INDEX
Explanations
topics related to immigration and border control
New Auto-Interp
Negative Logits
ultz
-0.18
urret
-0.15
é
-0.15
ercul
-0.14
tamb
-0.14
salopes
-0.14
arah
-0.14
izza
-0.14
uzz
-0.14
endor
-0.14
POSITIVE LOGITS
ovny
0.16
ODEV
0.16
ivec
0.15
avec
0.15
izada
0.15
origin
0.15
ClassName
0.15
:
0.15
åłĤ
0.14
æIJŀ
0.14
Activations Density 0.056%