INDEX
Explanations
references to comic book characters and their narrative arcs
New Auto-Interp
Negative Logits
_mE
-0.15
ussy
-0.15
ahat
-0.15
ramer
-0.15
Wenger
-0.14
ogi
-0.14
WB
-0.14
uien
-0.14
Tw
-0.14
ле
-0.14
POSITIVE LOGITS
Marvel
0.22
616
0.21
Nam
0.19
Marvel
0.18
inel
0.18
comics
0.18
209
0.17
AIM
0.17
Pun
0.16
Banner
0.16
Activations Density 0.093%