INDEX
Explanations
references to the Batman franchise and its characters
New Auto-Interp
Negative Logits
омен
-0.15
osa
-0.15
iggs
-0.14
Weber
-0.14
765
-0.14
trom
-0.14
uter
-0.14
NCY
-0.14
nc
-0.13
ATCH
-0.13
POSITIVE LOGITS
Gotham
0.39
Batman
0.38
Bat
0.36
Batman
0.36
Bat
0.33
bat
0.33
BAT
0.31
BAT
0.30
bat
0.28
bats
0.28
Activations Density 0.030%