INDEX
Explanations
references to presidential elections and campaigns
New Auto-Interp
Negative Logits
atters
-0.15
yun
-0.15
iferay
-0.15
tant
-0.15
esin
-0.14
PRES
-0.14
зÑĥ
-0.14
presets
-0.14
oven
-0.14
oS
-0.14
POSITIVE LOGITS
race
0.34
hopeful
0.27
race
0.26
Race
0.25
primary
0.24
Race
0.24
_race
0.22
Hope
0.21
primaries
0.21
primary
0.20
Activations Density 0.018%