Skip to main content

Adjust advanced settings

Adjust the advanced settings to have better control over generated output in Microsoft Excel. You can learn more in the OpenAI API documentation.
TermDefinition
TokenTokens can be thought of as pieces of words. During processing, the language model breaks down both the input (prompt) and the output (completion) texts into smaller units called tokens. Tokens generally correspond to ~4 characters of common English text. So 100 tokens are approximately worth 75 words. See how text is split into tokens.
Top PHelps adjust creativity level – Lower values result in more focused output, while higher values allow for more creative responses.
Frequency penalty (not available for Claude models)Penalizes tokens based on their frequency in the text so far – Higher values discourage the model from repeating the same tokens too frequently, as the more they appear in the text, the more penalized they get.
Presence penalty (not available for Claude models)Penalizes new tokens based on whether they appear in the text so far – Higher values encourage the model to use new tokens that are not penalized.
Prerequisites
You have created a Microsoft workbook and clicked GPT for Excel Word in the Home tab.
  1. In the GPT for Excel sidebar, click Settings from the GPT functions tab.


  2. Open the View advanced settings dropdown.


  3. Use the corresponding sliders to set the values for:

    • Top P: Adjust creativity by setting the value between 0 and 1.
      • Note: Set the creativity level to 1 when the value for Top P is lower than 1.
    • Frequency penalty: Set a penalty between 0 and 2 to apply to tokens each time they are repeated in the result.
    • Presence penalty: Set a one-time penalty between 0 and 2 for tokens that appear more than once in the result.

The advanced settings you defined are now the default for all GPT function executions. New executions will use these advanced settings.

Existing formulas will not automatically update to the new advanced settings if the cache is enabled. To re-execute them with different settings, you can either disable the cache, select the formulas and regenerate their results, or change a parameter in the formulas and press Enter.

What's next
Regenerate results for your GPT formulas to get results that take these new settings into account.