INDEX
Explanations
phrases indicating the passage of time or historical continuity
New Auto-Interp
Negative Logits
ixin
-0.16
essim
-0.15
Hlav
-0.15
ampus
-0.15
ube
-0.14
TB
-0.14
sb
-0.14
.SizeType
-0.14
èĬĻ
-0.14
urance
-0.14
POSITIVE LOGITS
رت
0.16
sted
0.15
ardash
0.14
è·
0.14
iglia
0.14
veau
0.14
æ²Ļ
0.14
ìĥī
0.14
Rud
0.14
azı
0.14
Activations Density 0.026%