INDEX
Explanations
mentions or comparisons involving political figures and elections
comparative statements related to political candidates
New Auto-Interp
Negative Logits
forwarded
-0.68
Signed
-0.64
${-0.62
ornia
-0.61
javascript
-0.61
":"/
-0.59
parted
-0.58
undercover
-0.57
Spo
-0.56
onding
-0.55
POSITIVE LOGITS
rivals
0.79
expectations
0.78
ensis
0.75
aurus
0.72
mson
0.69
competitors
0.68
verages
0.68
altogether
0.68
inctions
0.67
illac
0.67
Activations Density 0.410%