Skip to content

Keeping language models honest by directly eliciting knowledge encoded in their activations. Building on "Discovering latent knowledge in language models without supervision" (Burns et al. 2022)

active 2023-08-28 → 2023-09-18 (UTC)

Complete coverage28,108 / 28,108 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-10-29 (UTC)
Events
15
Pushes
13
Pull requests
1
Issues
0
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 22 days from 2023-08-28 to 2023-09-18. Pushes: 13 total, peak 6 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
derpyplops141310

Recent activity

Latest issues, pull requests and releases

  • Pull request#14derpyplops2023-08-30 22:45

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.