INDEX
Explanations
references to cultural elements and creative expressions in film
New Auto-Interp
Negative Logits
-
-0.17
sto
-0.16
ungal
-0.15
/
-0.15
Shin
-0.14
canonical
-0.14
barang
-0.14
A
-0.14
oon
-0.14
-
-0.14
POSITIVE LOGITS
еÑģÑı
0.19
lü
0.18
¡´
0.15
Çİ
0.15
dol
0.15
_ENCODING
0.15
erken
0.15
lut
0.14
Hait
0.14
Lans
0.14
Activations Density 0.316%