Building infrastructure for AI interpretability research 🤖 + 🧠 + 🔬
- Boston, US
-
13:34
(UTC -04:00)
Pinned Loading
-
ndif-team/ndif
ndif-team/ndif PublicThe NDIF server, which performs deep inference and serves nnsight requests remotely
-
ndif-team/nnsight
ndif-team/nnsight PublicThe nnsight package enables interpreting and manipulating the internals of deep learned models.
-
countermoral
countermoral PublicCounterMoral is a dataset designed to evaluate the effectiveness of model editing techniques in modifying moral judgments within language models. This dataset assesses moral judgments based on four…
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.