INDEX
Explanations
references to boys and related concepts
New Auto-Interp
Negative Logits
WriteBarrier
-0.70
WebControls
-0.69
compromisso
-0.67
Francesca
-0.66
feminina
-0.64
InputDecoration
-0.63
RUnlock
-0.63
Nü
-0.63
rime
-0.63
femminile
-0.63
POSITIVE LOGITS
boy
2.66
Boy
2.64
Boy
2.55
boy
2.48
BOY
2.47
BOY
2.38
boys
2.35
Boys
2.25
boys
2.20
Boys
2.13
Activations Density 0.071%