INDEX
Explanations
references to specific literary and film characters, particularly from classic literature and film adaptations
New Auto-Interp
Negative Logits
alf
-0.17
igham
-0.15
izr
-0.15
ül
-0.14
reator
-0.14
ulator
-0.14
CT
-0.14
ILES
-0.14
LLU
-0.13
ÎłÎ¿Î»Î¹
-0.13
POSITIVE LOGITS
tid
0.15
classic
0.15
á»ķ
0.15
EXTERNAL
0.15
Insensitive
0.14
(TEXT
0.14
INTERN
0.14
vert
0.14
_EXTERN
0.14
herit
0.14
Activations Density 0.047%