Skip to main content

safety-research/misalignment-indicators

SkillsMP has collected 1 skills from safety-research/misalignment-indicators. Open a skill to review its source and details.

Latest recorded source activity
SkillsMP catalog refreshed
skills collected
1
GitHub stars
9
GitHub forks
1

Skills in this repository

1 occupation categories · 100% classified

Showing 1 of 1 collected skills.

occupation
Data Scientists
description

Run the indicator-probe evaluation on bloom rollouts (any language / split) to produce probe token scores on GPU and then transcript-TPR/turn-FPR AUROC. Use when asked to "get probe scores", "run probe eval", "compute probe AUROC", reproduce the cross-lingual…

updated
Showing 1 of 1 collected skills.