INDEX
Explanations
mentions of a political party or its members
references to a specific political party or organization
New Auto-Interp
Negative Logits
ĸļ
-0.71
ãĥīãĥ©ãĤ´ãĥ³
-0.66
cgi
-0.65
gers
-0.65
ascript
-0.64
gor
-0.64
Revel
-0.63
ization
-0.63
izations
-0.62
ç·
-0.61
POSITIVE LOGITS
daq
1.00
jriwal
0.87
ointment
0.82
iflower
0.81
icter
0.79
elsius
0.72
bay
0.71
kson
0.71
rower
0.71
les
0.71
Activations Density 0.043%