INDEX
Explanations
mentions of film direction and production roles
New Auto-Interp
Negative Logits
472
-0.16
agate
-0.15
anner
-0.15
out
-0.15
åĩ
-0.15
alf
-0.14
è¾°
-0.14
imately
-0.14
preference
-0.14
uw
-0.14
POSITIVE LOGITS
iger
0.18
eker
0.18
HEMA
0.16
ninger
0.16
ÑĢд
0.16
afone
0.16
reon
0.15
Eag
0.15
"display
0.15
ÙĦÙĪØ¨
0.15
Activations Density 0.020%