INDEX
Explanations
mentions of specific individuals and their achievements or contributions
New Auto-Interp
Negative Logits
inja
-0.15
ault
-0.15
lock
-0.14
itti
-0.14
obb
-0.14
STRU
-0.14
ppe
-0.13
este
-0.13
ckett
-0.13
ÑģÑĤÑĢи
-0.13
POSITIVE LOGITS
ometown
0.17
luet
0.17
angstrom
0.16
_tac
0.16
одÑĥ
0.16
iom
0.15
æ´»
0.15
emmel
0.14
ardy
0.14
contres
0.14
Activations Density 0.505%