INDEX
Explanations
the word "Gay" in various contexts
occurrences of the word "Gay."
New Auto-Interp
Negative Logits
sight
-0.77
igslist
-0.77
arily
-0.72
ariat
-0.68
depth
-0.67
miser
-0.67
captcha
-0.66
orage
-0.65
İĭ
-0.65
fertil
-0.65
POSITIVE LOGITS
lee
1.12
lene
1.03
sey
1.00
dos
0.99
lynn
0.98
lyn
0.92
quet
0.92
la
0.92
leigh
0.89
rier
0.89
Activations Density 0.041%