INDEX
Explanations
phrases mentioning the name "Kate."
occurrences of the name "Kate."
New Auto-Interp
Negative Logits
oresc
-0.76
ribution
-0.75
ATIONS
-0.74
cffff
-0.74
affili
-0.73
avez
-0.73
ocre
-0.73
cipline
-0.73
ribune
-0.73
ornia
-0.72
POSITIVE LOGITS
Upton
1.03
McCann
0.96
Kate
0.91
Wins
0.91
Stein
0.84
Manuel
0.82
Mara
0.82
Hanna
0.82
Kate
0.81
Wallace
0.80
Activations Density 0.004%