INDEX
Explanations
mentions of specific locations or hometowns
New Auto-Interp
Negative Logits
aghan
-0.16
ombo
-0.15
toa
-0.15
orns
-0.15
YSQL
-0.14
EMU
-0.14
모
-0.14
acco
-0.14
KEEP
-0.14
BJECT
-0.14
POSITIVE LOGITS
ald
0.17
ahl
0.16
ÙİØŃ
0.15
elter
0.14
aver
0.14
enan
0.14
gel
0.14
aza
0.13
otre
0.13
Sent
0.13
Activations Density 0.001%