INDEX
Explanations
terms related to refugees and migration issues
New Auto-Interp
Negative Logits
ữ
-0.16
Lans
-0.15
ÏĦι
-0.14
fak
-0.14
iker
-0.14
alance
-0.13
کد
-0.13
že
-0.13
riday
-0.13
ten
-0.13
POSITIVE LOGITS
quit
0.22
tom
0.22
bif
0.21
rall
0.20
franch
0.20
chute
0.20
dispar
0.19
pass
0.19
rent
0.18
atte
0.18
Activations Density 0.024%