INDEX
Explanations
references to specific legislative bills or measures
New Auto-Interp
Negative Logits
åĪĹ
-0.16
á»ı
-0.15
Bonus
-0.15
plash
-0.15
ylie
-0.15
ESH
-0.14
chester
-0.14
cheng
-0.14
SKIP
-0.13
渡
-0.13
POSITIVE LOGITS
áf
0.16
Nurs
0.16
locale
0.15
obot
0.14
921
0.14
lemen
0.14
Bowman
0.14
Ø´ÙĪ
0.14
divert
0.13
chw
0.13
Activations Density 0.027%