INDEX
Explanations
mentions of Ukraine and its related terms
New Auto-Interp
Negative Logits
indre
-0.16
erah
-0.15
inand
-0.15
berger
-0.15
anded
-0.15
CHED
-0.15
Dann
-0.15
s
-0.15
anding
-0.14
å¥ij
-0.14
POSITIVE LOGITS
Crimea
0.19
Kiev
0.18
etz
0.18
Ukr
0.18
kee
0.17
hry
0.17
amen
0.17
Maid
0.16
984
0.15
Lv
0.15
Activations Density 0.005%