INDEX
Explanations
character names and their roles in movies
New Auto-Interp
Negative Logits
stÅĻÃŃ
-0.17
://'
-0.17
antry
-0.16
validator
-0.14
heed
-0.14
$č↵
-0.13
pole
-0.13
sân
-0.13
ære
-0.13
ylon
-0.13
POSITIVE LOGITS
Indexed
0.15
avez
0.14
igm
0.14
Tess
0.14
ük
0.14
oric
0.14
component
0.14
adb
0.13
Pub
0.13
ellar
0.13
Activations Density 0.015%