INDEX
Explanations
references to legislative bills and governmental policies
New Auto-Interp
Negative Logits
è¶Ĭ
-0.16
ivar
-0.16
bast
-0.15
iben
-0.15
cdn
-0.14
rix
-0.14
Bast
-0.14
нап
-0.14
rob
-0.13
Suff
-0.13
POSITIVE LOGITS
Dün
0.16
欣
0.15
oblin
0.15
åħģ
0.15
retty
0.15
-gnu
0.15
azzi
0.14
allowing
0.14
одав
0.14
ultip
0.14
Activations Density 0.090%