Selecting a specific word from x amount of probable words?

Using the “n” parameter with max_tokens set to 1 will give you a list of probable words to operate on, but I was wondering if there was another way.

Is there a less expensive way to select a specific word from a list of the probable words?

1 Like

I believe you are looking for logit_bias

Awesome, thanks! I’ll read it.

1 Like