INDEX
Explanations
the name "Anna"
references to the name "Anna" in various contexts
New Auto-Interp
Negative Logits
enegger
-0.81
ours
-0.78
asters
-0.75
aneously
-0.74
inct
-0.71
igious
-0.70
staff
-0.70
awar
-0.69
ribution
-0.68
ember
-0.68
POSITIVE LOGITS
Karen
0.90
Maria
0.85
Pa
0.83
ette
0.82
Nicole
0.82
uthor
0.80
oice
0.80
Kendrick
0.79
Anna
0.76
Anth
0.75
Activations Density 0.009%