INDEX
Explanations
references to political candidates and their campaigns
New Auto-Interp
Negative Logits
ubar
-0.20
658
-0.15
ehler
-0.15
ovsky
-0.15
489
-0.15
otton
-0.14
_CSR
-0.14
ariat
-0.14
justification
-0.14
HEMA
-0.14
POSITIVE LOGITS
promises
0.15
promise
0.15
vision
0.15
Values
0.14
VALUES
0.14
endor
0.14
values
0.14
endors
0.14
kas
0.14
Vision
0.14
Activations Density 0.167%