INDEX
Explanations
references to superhero characters and their appearances
New Auto-Interp
Negative Logits
輪
-0.15
Clem
-0.14
mats
-0.14
Sab
-0.14
.timing
-0.14
955
-0.14
_fg
-0.14
antro
-0.14
Barney
-0.14
emoc
-0.14
POSITIVE LOGITS
Clark
0.38
Superman
0.38
Clark
0.34
Lois
0.32
Lex
0.31
Lex
0.28
Kent
0.26
Kal
0.25
Super
0.24
lex
0.24
Activations Density 0.020%