wassname/moral-maps
1
0
Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-09-21 13:10:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove dead steering score link

Browse Source 
Keep the proposed metric name as plain text because Steering Lite no longer has the linked section.

Co-Authored-By: PI/gpt-6-astra <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-09-17 14:05:21 +08:00
co-authored by PI/gpt-6-astra
parent da2e70f3bb
commit 8088f774cd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -60,7 +60,7 @@ For steering comparisons, we also want a score that considers both intended chan
When we steer a concept, we want the relevant answers to change without changing unrelated answers. So we reward movement in the intended direction and subtract a smaller penalty for side effects. We use logprobs because they show small changes even when the model still chooses the same answer.
A possible replacement is [steering F-beta](https://github.com/wassname/steering-lite#a-simpler-score), which treats desired changes as true positives and unwanted changes as false positives. It is still a proposal; the plots and existing results have not been rescored.
A possible replacement is steering F-beta, which treats desired changes as true positives and unwanted changes as false positives. It is still a proposal; the plots and existing results have not been rescored.
## Install and use