INDEX
Explanations
female names
occurrences of the name "Anna."
New Auto-Interp
Negative Logits
enegger
-0.81
aneously
-0.77
inct
-0.75
ember
-0.73
urtle
-0.71
ours
-0.71
ierrez
-0.71
ModLoader
-0.69
ribute
-0.69
ulhu
-0.69
POSITIVE LOGITS
Karen
0.94
Maria
0.91
uthor
0.85
Nicole
0.82
Kendrick
0.81
ette
0.80
Anna
0.79
oice
0.78
abel
0.78
esthesia
0.77
Activations Density 0.011%