INDEX
Explanations
references to graphic novels and their characteristics
New Auto-Interp
Negative Logits
akhir
-0.14
Ing
-0.14
630
-0.14
/|
-0.14
usher
-0.14
invent
-0.14
erra
-0.13
.ll
-0.13
chụp
-0.13
æ¼Ķ
-0.13
POSITIVE LOGITS
comics
0.45
Comics
0.42
comic
0.41
graphic
0.35
comic
0.33
strip
0.33
strips
0.32
Sequential
0.31
Graphic
0.31
Comic
0.30
Activations Density 0.119%