INDEX
Explanations
references to strong female characters and their roles in media
New Auto-Interp
Negative Logits
AspNetCore
-0.46
Italijanski
-0.43
AnchorStyles
-0.41
ClientSize
-0.40
defaultstate
-0.39
liothèque
-0.38
DbType
-0.38
LVANIA
-0.36
Anhalt
-0.36
namics
-0.36
POSITIVE LOGITS
mutants
0.78
mutant
0.74
Wolverine
0.69
Cyclops
0.67
mutation
0.63
Xavier
0.62
Wolverine
0.60
Mutant
0.60
Mut
0.59
Mut
0.59
Activations Density 0.382%