INDEX
Explanations
mentions of legal terms and judicial processes
New Auto-Interp
Negative Logits
عاÙħ
-0.15
ãĥ¼ãĥĢ
-0.14
649
-0.14
_macros
-0.14
_rp
-0.14
lÃŃÄį
-0.14
isko
-0.13
++)↵
-0.13
INCT
-0.13
antine
-0.13
POSITIVE LOGITS
Bench
0.23
Chief
0.23
CJ
0.22
Chief
0.21
bench
0.21
bench
0.21
Colleg
0.21
judges
0.20
colleg
0.20
jud
0.20
Activations Density 0.025%