INDEX
Explanations
references to countries and their related contexts, such as demographics, economics, or political issues
New Auto-Interp
Negative Logits
idel
-0.17
roid
-0.16
óln
-0.15
urse
-0.15
ommen
-0.15
clist
-0.15
berapa
-0.14
umer
-0.14
anned
-0.14
oster
-0.14
POSITIVE LOGITS
there
0.17
à¥įवव
0.15
ิศ
0.15
ìĦł
0.15
671
0.14
untu
0.14
ubi
0.14
aru
0.14
CHE
0.13
Til
0.13
Activations Density 0.133%