INDEX
Explanations
references to the "X-Men" franchise and its characters
New Auto-Interp
Negative Logits
beg
-0.15
اÙģØª
-0.15
shirt
-0.15
omon
-0.14
confl
-0.14
<+
-0.14
weet
-0.14
azzi
-0.13
IFT
-0.13
hir
-0.13
POSITIVE LOGITS
plode
0.19
DownList
0.15
plorer
0.15
ึ
0.15
ÑĤаÑħ
0.15
дÑĢÑĥго
0.14
oÃłi
0.14
elik
0.14
IIIK
0.14
eka
0.14
Activations Density 0.043%