INDEX
Explanations
keywords related to legal proceedings or trials
references to legal trials
New Auto-Interp
Negative Logits
ula
-0.76
orns
-0.75
olen
-0.72
ulic
-0.69
lav
-0.68
otle
-0.66
licks
-0.66
kell
-0.65
oji
-0.63
flush
-0.62
POSITIVE LOGITS
eer
0.89
eering
0.87
hearings
0.82
Trials
0.76
neys
0.76
imony
0.75
judge
0.75
indict
0.73
Proceedings
0.72
testimony
0.71
Activations Density 0.020%