[savant_penguin]

1. Incorrect. The output of the decoder LLM is the probability distribution of the next token given the input text. Temperature=0 means that the output distribution is not pushed to be closer to a uniform distribution. The randomness comes from the sampling of the next token according to the output distribution to generate text. If you want determinism you always get the argmax of the distribution.

[gliptic]

Incorrect. The output of the decoder LLM is logits that are then divided by the temperature and passed through softmax to give the probabilities. You can't actually set temperature to 0 (division by zero), but in the limit where temperature approaches 0, softmax converges to argmax.

Temperature = 1 is where it's not pushed in either direction.