Interpreting GPT: the logit lens – LessWrong(2020) (lesswrong.com)

2 points by nalinidash 1y ago ↗ HN

0 comments

[ 1.4 ms ] story [ 9.3 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats