INDEX
Explanations
legal terminology and references to court proceedings
New Auto-Interp
Negative Logits
Prosec
-0.21
prosecution
-0.17
prosec
-0.17
prosecuting
-0.17
prosecute
-0.17
дап
-0.17
zel
-0.17
prosecuted
-0.16
çĿ£
-0.15
-dot
-0.15
POSITIVE LOGITS
court
0.57
courts
0.51
Court
0.47
court
0.42
Court
0.42
Circuit
0.41
circuit
0.41
cour
0.40
judge
0.39
-court
0.38
Activations Density 0.276%