INDEX
Explanations
terms related to leftist political ideology and movements
New Auto-Interp
Negative Logits
ae
-0.18
.epam
-0.16
inz
-0.15
ady
-0.15
Silk
-0.15
posite
-0.14
ะ
-0.14
rna
-0.14
dued
-0.14
akash
-0.14
POSITIVE LOGITS
/right
0.22
-handed
0.20
ward
0.20
-hand
0.20
-wing
0.20
s
0.20
wing
0.18
wards
0.18
ycler
0.17
most
0.17
Activations Density 0.039%