INDEX
Explanations
mentions of Turkey and its associations with Turkish entities or support in various contexts
New Auto-Interp
Negative Logits
jad
-0.19
egers
-0.19
Bölüm
-0.16
ranÃŃ
-0.16
úsqueda
-0.15
rani
-0.15
/bus
-0.15
ardon
-0.15
Ú¯ÛĮر
-0.14
illac
-0.14
POSITIVE LOGITS
Tat
0.16
dden
0.16
ken
0.15
undy
0.15
prung
0.14
Stra
0.14
Bey
0.14
ham
0.14
anks
0.14
entine
0.14
Activations Density 0.012%