A question for those of you who know the OpenAI playground.

When on complete mode, what does “\n” mean (image below) and also  what does “Total: -0.89 ….”  And the rest below that mean? 

I’m a non techie who needs to understand…

Recovering Film Studio Exec l Psychology Nerd l Strategy Muse l Brand Builder l Also, “Culture eats strategy for breakfast.” - Peter Drucker   JoinSavvyAvi.com

Data scientist. Interested in most of the kinds of things that job implies, among others.

I’m asking because I’m writing a short post about how LLMs work and want to explain the probabilities which makes sense for the words displayed but don’t obviously add up to a 100 even if one bucket is “all other possibilities” which I don’t see. 

Why does next line have a probability?

The log probability bit is just about how the output is natively represented. For math reasons (differentiable loss functions) the model outputs the log of the probabilities. You can reverse this by taking e ^ (-0.89) ~= 41.27%

Full-stack web3 developer, learn more about my projects here: https://github.com/tempe-techie

\n means new line

As for the rest, afaik LLMs try to predict the next word when they are writing a reply. So in this case the LLM predicted that the next word after "ran" should be "after".