INDEX
Explanations
names of legal officials, such as judges, and legal terms associated with court proceedings
New Auto-Interp
Negative Logits
haar
-0.74
Rivals
-0.73
ohyd
-0.73
rolet
-0.73
ulus
-0.72
Roads
-0.69
abwe
-0.67
amily
-0.66
Horde
-0.66
kefeller
-0.65
POSITIVE LOGITS
presiding
1.09
overseeing
0.99
ruled
0.92
rulings
0.89
jud
0.88
rooms
0.86
Advocate
0.84
Gorsuch
0.80
judge
0.80
sentenced
0.79
Activations Density 0.064%