INDEX
Explanations
elements related to superhero themes and character dynamics
New Auto-Interp
Negative Logits
azzo
-0.15
oje
-0.15
ãĥ¾
-0.15
mtree
-0.15
éŃĤ
-0.14
ogn
-0.14
ÙģØ§Ø±
-0.14
å¦ĥ
-0.14
鬼
-0.14
çļĩ
-0.14
POSITIVE LOGITS
super
0.43
Super
0.35
superhero
0.35
super
0.35
cape
0.33
vigil
0.32
Super
0.31
superheroes
0.31
hero
0.30
SUPER
0.30
Activations Density 0.219%