INDEX
Explanations
mentions of people's names
mentions of the name "Nathan" in various contexts
New Auto-Interp
Negative Logits
ative
-0.87
essee
-0.77
tesy
-0.70
omething
-0.67
20439
-0.65
ership
-0.63
boa
-0.63
,,,,
-0.63
ators
-0.63
going
-0.60
POSITIVE LOGITS
elson
1.04
Hale
0.94
Drake
0.90
Cohn
0.89
Grayson
0.85
Silver
0.85
Freed
0.85
Diaz
0.84
Rothschild
0.84
Mayer
0.81
Activations Density 0.067%