INDEX
Explanations
names of characters in movies and their associated roles
New Auto-Interp
Negative Logits
esel
-0.17
_ctor
-0.15
ajs
-0.15
createAction
-0.15
оди
-0.14
priv
-0.14
аÑĢÑĸ
-0.14
تاب
-0.14
xad
-0.14
urma
-0.14
POSITIVE LOGITS
oro
0.18
Flem
0.15
æĬ
0.15
rolling
0.14
ã
0.14
Wass
0.13
gaard
0.13
mp
0.13
Alv
0.13
rolling
0.13
Activations Density 0.019%