INDEX
Explanations
the name "Kate" mentioned in the text
mentions of the name "Kate."
New Auto-Interp
Negative Logits
ensed
-0.84
oresc
-0.83
cffff
-0.81
notation
-0.80
iple
-0.78
ornia
-0.77
ribution
-0.77
orescence
-0.76
ATIONS
-0.76
cipl
-0.75
POSITIVE LOGITS
Upton
1.06
McCann
0.93
Wins
0.92
Stein
0.87
Turner
0.86
Moss
0.84
Fisher
0.83
Kane
0.82
Mara
0.82
vich
0.82
Activations Density 0.008%