INDEX
Explanations
phrases related to political or social opposition and conflict
references to combating various threats or challenges
New Auto-Interp
Negative Logits
chell
-0.94
gow
-0.84
overed
-0.79
OGR
-0.78
chart
-0.77
Cosponsors
-0.75
holm
-0.73
pool
-0.72
ophe
-0.72
pots
-0.72
POSITIVE LOGITS
austerity
0.75
modernization
0.73
behalf
0.72
against
0.67
independence
0.67
them
0.65
anybody
0.64
divine
0.64
illiter
0.64
extremism
0.63
Activations Density 0.049%