INDEX
Explanations
names of actors and their roles in movies
New Auto-Interp
Negative Logits
æĶ
-0.17
cầm
-0.17
.gwt
-0.15
SizePolicy
-0.14
éľĩ
-0.14
seznam
-0.14
oad
-0.14
ÃŃsk
-0.13
lr
-0.13
oppers
-0.13
POSITIVE LOGITS
Affero
0.18
ninger
0.16
ressing
0.15
ingle
0.14
Jerusalem
0.14
ůl
0.14
linger
0.14
åľĴ
0.14
Kes
0.14
lý
0.14
Activations Density 0.022%