INDEX
Explanations
references to "guy" and "guys" in the text
New Auto-Interp
Negative Logits
Palin
-0.73
Datuak
-0.68
*-*-
-0.68
μων
-0.67
Mab
-0.65
なりません
-0.64
ATA
-0.64
dataclass
-0.63
PAP
-0.63
Met
-0.62
POSITIVE LOGITS
guys
1.52
guys
1.48
GUYS
1.40
Guys
1.36
guy
1.33
Guys
1.30
GUY
1.22
guy
1.20
gars
1.11
GUY
1.07
Activations Density 0.069%