INDEX
Explanations
topics related to societal structures and governance
New Auto-Interp
Negative Logits
umb
-0.15
ederland
-0.15
fty
-0.14
iar
-0.14
uggy
-0.14
aldi
-0.14
whereas
-0.14
çünkü
-0.14
Neighbor
-0.14
Hüs
-0.14
POSITIVE LOGITS
like
0.18
unlike
0.18
ï¼īãģ¯
0.16
along
0.16
along
0.15
bote
0.15
meanwhile
0.14
ervers
0.14
oon
0.14
кÑĢаÑĹ
0.14
Activations Density 0.258%