INDEX
Explanations
mentions of the name "Jane"
references to the name "Jane."
New Auto-Interp
Negative Logits
orescent
-0.89
ctic
-0.82
fecture
-0.81
rophic
-0.81
ulative
-0.79
doors
-0.79
rophe
-0.74
ulatory
-0.74
*/(
-0.73
igious
-0.72
POSITIVE LOGITS
Jane
1.27
Doe
1.19
Jane
1.12
Leilan
0.88
Waters
0.85
Seymour
0.81
Rosenthal
0.80
Gad
0.79
Barton
0.77
Anne
0.77
Activations Density 0.007%