INDEX
Explanations
quoted text, including dialogue and titles
New Auto-Interp
Negative Logits
aran
-0.16
asil
-0.16
irts
-0.15
stro
-0.15
ubyte
-0.14
Broad
-0.14
ubl
-0.14
Estate
-0.14
ra
-0.14
972
-0.14
POSITIVE LOGITS
avy
0.17
valuator
0.15
.childNodes
0.15
çıį
0.14
êµ
0.14
Lint
0.14
lops
0.14
etrofit
0.14
alf
0.14
éĻ
0.13
Activations Density 0.081%