INDEX
Explanations
mentions of legal entities such as courts
mentions of various courts in the United States
New Auto-Interp
Negative Logits
ku
-0.70
ubi
-0.68
ocument
-0.66
ecd
-0.64
eco
-0.64
eele
-0.63
utable
-0.63
todd
-0.61
anguages
-0.60
ec
-0.60
POSITIVE LOGITS
judge
1.08
Judge
1.03
rooms
1.03
room
0.90
auld
0.84
Circuit
0.84
Judge
0.83
magistrate
0.82
Clerk
0.82
martial
0.82
Activations Density 0.048%