INDEX
Explanations
references to the name "Donna."
references to specific individuals, particularly women named Donna
New Auto-Interp
Negative Logits
*/(
-1.10
manship
-1.01
mble
-0.96
edom
-0.91
ahead
-0.90
thumbnails
-0.81
utenberg
-0.80
nesota
-0.80
ugu
-0.78
ictions
-0.76
POSITIVE LOGITS
Grande
0.94
Braz
0.88
Donna
0.83
Ping
0.77
Veronica
0.76
Betty
0.75
Wilde
0.73
Gaga
0.71
Lauren
0.71
Bella
0.69
Activations Density 0.020%