INDEX
Explanations
references to critical evaluations or analyses of films
New Auto-Interp
Negative Logits
Vak
-0.16
angu
-0.14
éric
-0.14
licas
-0.14
Disposition
-0.13
edin
-0.13
interop
-0.13
оÑĤв
-0.13
disastr
-0.13
asio
-0.13
POSITIVE LOGITS
cit
0.24
afirm
0.23
dice
0.22
affirm
0.22
cita
0.21
iron
0.21
menc
0.20
señ
0.20
mention
0.20
relat
0.19
Activations Density 0.085%