INDEX
Explanations
terms related to legislative processes and societal impacts of laws
New Auto-Interp
Negative Logits
als
-0.16
ze
-0.15
éĥ
-0.14
kin
-0.14
ibo
-0.14
(
-0.14
VT
-0.14
gib
-0.13
ovel
-0.13
support
-0.13
POSITIVE LOGITS
inho
0.15
adel
0.15
buckets
0.15
Scar
0.14
astreet
0.14
uhe
0.14
ucz
0.14
pleado
0.14
<!--[
0.14
lož
0.14
Activations Density 0.024%