INDEX
Explanations
mentions of significant historical events or entities
New Auto-Interp
Negative Logits
dated
-0.20
dating
-0.18
dating
-0.18
Ferguson
-0.17
æĹ¥æľŁ
-0.17
circa
-0.16
854
-0.15
_date
-0.15
odor
-0.15
леÑĢг
-0.15
POSITIVE LOGITS
ìĶ
0.16
chia
0.15
uhn
0.15
foy
0.15
ÑĤÑĢо
0.15
æ±
0.14
asz
0.14
айд
0.14
oyal
0.14
adel
0.14
Activations Density 0.278%