INDEX
Explanations
mentions of legal proceedings or courtroom-related terms
New Auto-Interp
Negative Logits
dayName
-0.70
kun
-0.68
href
-0.66
erenn
-0.65
Tik
-0.63
zl
-0.63
since
-0.62
Bus
-0.61
Else
-0.61
ãĤ¦
-0.61
POSITIVE LOGITS
verdict
0.90
jury
0.87
deliberations
0.86
glass
0.82
acquitted
0.80
deliber
0.80
convened
0.79
jurors
0.77
member
0.75
convict
0.75
Activations Density 0.011%