INDEX
Explanations
references to strong female characters in stories
New Auto-Interp
Negative Logits
okuyayım
-0.55
Geplaatst
-0.50
avyzd
-0.49
traite
-0.49
rafa
-0.48
ussis
-0.48
getDrawable
-0.47
partid
-0.47
cedo
-0.47
quello
-0.46
POSITIVE LOGITS
protagonist
0.81
tartalomajánló
0.68
SourceChecksum
0.66
héros
0.65
(!__
0.58
主人公
0.57
adventures
0.57
hero
0.56
#!/
0.54
herói
0.53
Activations Density 0.254%