INDEX
Explanations
words related to citizens or citizenship
mentions of "citizen" or "citizens" in various contexts
New Auto-Interp
Negative Logits
ENDED
-0.86
otherapy
-0.77
SourceFile
-0.74
ension
-0.72
Solution
-0.69
ologies
-0.66
Prev
-0.66
ended
-0.65
hiba
-0.65
EDIT
-0.65
POSITIVE LOGITS
hip
0.97
hips
0.90
folk
0.85
residing
0.85
citizen
0.80
rified
0.79
ry
0.79
citizens
0.74
hood
0.72
Citizens
0.71
Activations Density 0.024%