INDEX
Explanations
mentions of the name "Kate"
references to a specific person named Kate
New Auto-Interp
Negative Logits
oresc
-0.76
affili
-0.72
ocre
-0.68
avez
-0.67
otin
-0.67
ribution
-0.67
cipline
-0.66
ensed
-0.65
systematic
-0.64
ornia
-0.64
POSITIVE LOGITS
Kate
1.06
McCann
1.00
Upton
0.94
Kate
0.94
Wins
0.85
Mara
0.84
Browne
0.82
patrick
0.80
Manuel
0.78
Hogan
0.76
Activations Density 0.004%