[thatjoeoverthr]

More broadly, it’s not trained to have any self awareness and this is a factor in other “hallucinations”. If you ask, for example, to describe the “marathon crater”, it doesn’t recognize that there’s no such thing in its corpus, but will instead start by writing an answer (“sure! The marathon crater is..”) and freestyle from there. Same if you ask it why it did something, or details about itself, etc. You should access one directly (not through an app like chatGPT) and build a careful suite of tests to learn more. Really fascinating.

[_delirium]

Yes, there’s research showing that models’ self-assessment of probabilities (when you ask them via prompting) don’t even match the same models’ actual probabilities, in cases where you can measure the probabilities directly (e.g. by looking at the logits): https://arxiv.org/abs/2305.13264

[anon291]

Logits are not probabilities... at least not in the way you understand probability. Probabilities mathematically are anything that broadly behaves like a probability, whereas colloquially probabilities represent the likelihood or the preponderance of a particular phenomenon. Logits are not either of those.

[_delirium]

The probability of token generation is a function of the logits. Do you have an actual point related to the linked paper?

[anon291]

That is one way of sampling tokens. It is not the only way. Logits do not map neatly to belief, although it is convenient to behave as if they do