INDEX
Explanations
political party affiliations and voting patterns
New Auto-Interp
Negative Logits
ife
-0.14
undle
-0.14
tom
-0.14
.tom
-0.14
tom
-0.14
ollen
-0.14
tens
-0.14
play
-0.13
ph
-0.13
aines
-0.13
POSITIVE LOGITS
abel
0.16
.CustomButton
0.15
hta
0.15
liš
0.15
Convention
0.14
ograf
0.14
림
0.14
è̳
0.14
åģ¥
0.14
aidu
0.14
Activations Density 0.136%