INDEX
Explanations
legislative bills and their sponsors
New Auto-Interp
Negative Logits
irie
-0.16
ire
-0.16
iram
-0.16
ulary
-0.15
-INF
-0.15
icz
-0.15
str
-0.14
usercontent
-0.14
oy
-0.14
Amb
-0.14
POSITIVE LOGITS
snd
0.16
ieder
0.15
ató
0.15
à¹Īà¸Ńม
0.15
_ps
0.14
تس
0.14
ÑĤин
0.14
uvo
0.14
ecessary
0.13
Ess
0.13
Activations Density 0.009%