INDEX
Explanations
references to legislative bills and legislation
New Auto-Interp
Negative Logits
олÑı
-0.16
subs
-0.15
ics
-0.15
escal
-0.14
Abb
-0.14
_HIDDEN
-0.14
bal
-0.14
izzo
-0.13
cord
-0.13
Abb
-0.13
POSITIVE LOGITS
aren
0.16
iards
0.15
tent
0.15
boards
0.15
ermo
0.14
Å©
0.14
коÑĤ
0.14
acct
0.14
ardım
0.14
astro
0.14
Activations Density 0.038%