INDEX
Explanations
terms related to political parties and their dynamics
New Auto-Interp
Negative Logits
ister
-0.17
nect
-0.17
اتÛĮ
-0.16
lei
-0.16
598
-0.16
626
-0.15
array
-0.15
lea
-0.15
erguson
-0.15
ist
-0.15
POSITIVE LOGITS
ing
0.22
ÄĽÅ¾
0.17
ING
0.17
vsp
0.17
oret
0.16
ynom
0.15
isans
0.15
ament
0.15
odesk
0.15
/part
0.14
Activations Density 0.027%