INDEX
Explanations
mentions of fame and well-known individuals or entities
New Auto-Interp
Negative Logits
éĥİ
-0.18
153
-0.17
als
-0.17
itzer
-0.16
ayo
-0.16
brook
-0.15
ichert
-0.15
umin
-0.15
isan
-0.15
acz
-0.15
POSITIVE LOGITS
/not
0.20
/pop
0.19
-brand
0.17
landmarks
0.17
âĢĮترÛĮÙĨ
0.16
faces
0.16
among
0.16
esco
0.16
/original
0.15
-name
0.14
Activations Density 0.034%