INDEX
Explanations
mentions of award nominations and categories related to films
New Auto-Interp
Negative Logits
innie
-0.15
.opensource
-0.15
ntag
-0.15
oppins
-0.14
anio
-0.14
èĩ
-0.13
orno
-0.13
FT
-0.13
agus
-0.13
andon
-0.13
POSITIVE LOGITS
hlen
0.14
tron
0.14
borg
0.14
Phoenix
0.13
Exc
0.13
untime
0.13
afen
0.13
Spicer
0.13
Opr
0.13
iones
0.13
Activations Density 0.014%