INDEX
Explanations
mentions of film releases and notable cinematic elements
New Auto-Interp
Negative Logits
uce
-0.16
asher
-0.16
Rus
-0.15
kanal
-0.15
izard
-0.15
iral
-0.14
ger
-0.14
alu
-0.14
Gerard
-0.14
shal
-0.14
POSITIVE LOGITS
اÙĦعظ
0.18
اضÙĬ
0.16
ặ
0.16
enburg
0.15
oola
0.14
alian
0.14
ools
0.14
verileri
0.14
omik
0.14
ONGL
0.13
Activations Density 0.148%