How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. (arXiv:2305.00586v5 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2305.00586 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.