INDEX
Explanations
indicators of genre and classification in media content
New Auto-Interp
Negative Logits
onet
-0.17
encias
-0.15
encia
-0.15
itsu
-0.15
bole
-0.14
Rare
-0.14
reater
-0.14
imb
-0.14
ales
-0.13
quir
-0.13
POSITIVE LOGITS
lán
0.15
ôt
0.15
ForObject
0.14
910
0.14
arness
0.14
950
0.13
gesch
0.13
нÑĸвеÑĢ
0.13
633
0.13
æ³³
0.13
Activations Density 0.000%