INDEX
Explanations
mentions of historical figures and their contributions to various fields
New Auto-Interp
Negative Logits
indre
-0.15
ele
-0.15
éĽĦ
-0.14
_DOM
-0.14
ÑĨик
-0.14
ussen
-0.13
readcr
-0.13
icot
-0.13
bios
-0.13
ãģķ
-0.13
POSITIVE LOGITS
modern
0.23
today
0.19
å¾Įãģ®
0.19
adlo
0.17
tod
0.17
lay
0.16
modern
0.16
moderne
0.16
ä»Ĭ天
0.16
Modern
0.16
Activations Density 0.188%