INDEX
Explanations
comparisons involving test results and metrics
New Auto-Interp
Negative Logits
ToFit
-0.17
anne
-0.14
uchen
-0.14
@update
-0.14
-proxy
-0.14
temper
-0.14
obia
-0.14
behold
-0.13
ucch
-0.13
chip
-0.13
POSITIVE LOGITS
memcmp
0.20
comparison
0.20
expectations
0.18
comparison
0.18
Compare
0.18
match
0.18
comparisons
0.17
Compare
0.17
matches
0.17
comparing
0.17
Activations Density 0.117%