INDEX
Explanations
references to specific historical periods or classifications in film
New Auto-Interp
Negative Logits
ãģķãĤĵãģ¯
-0.15
nn
-0.15
206
-0.15
sher
-0.14
piel
-0.14
Gül
-0.14
FieldType
-0.13
åIJ¦
-0.13
ooter
-0.13
orney
-0.13
POSITIVE LOGITS
idor
0.15
ere
0.14
!=(
0.14
_MATH
0.14
éģ
0.14
|--
0.13
ãĥ³ãĥIJ
0.13
Dub
0.13
PTY
0.13
ificar
0.13
Activations Density 0.008%