INDEX
Explanations
references to specific years and legislative acts
New Auto-Interp
Negative Logits
olas
-0.16
arf
-0.15
olet
-0.15
atas
-0.15
istrovstvÃŃ
-0.14
itage
-0.13
мог
-0.13
:::
-0.13
Vien
-0.13
onte
-0.13
POSITIVE LOGITS
illes
0.18
.rt
0.16
Sy
0.15
UDGE
0.15
thur
0.14
uddle
0.14
endum
0.13
/respond
0.13
aha
0.13
OST
0.13
Activations Density 0.013%