INDEX
Explanations
references to comic books
references to comic books
New Auto-Interp
Negative Logits
ntil
-0.93
edIn
-0.76
undai
-0.76
achev
-0.75
qv
-0.75
sembly
-0.75
ldon
-0.74
rake
-0.74
animous
-0.74
bek
-0.73
POSITIVE LOGITS
book
0.90
strip
0.90
Comics
0.88
relief
0.88
comic
0.82
book
0.81
strip
0.81
shorts
0.78
strips
0.78
sans
0.78
Activations Density 0.018%