INDEX
Explanations
mentions of the name "Gregory."
New Auto-Interp
Negative Logits
yd
-0.17
illery
-0.16
illac
-0.15
yz
-0.15
ilib
-0.15
Hem
-0.14
Hang
-0.14
WithIdentifier
-0.14
æĮ¯ãĤĬ
-0.14
ErrorException
-0.14
POSITIVE LOGITS
orio
0.18
orian
0.18
fik
0.17
ius
0.16
itional
0.15
oire
0.15
erate
0.15
nd
0.15
rame
0.15
ty
0.14
Activations Density 0.043%