INDEX
Explanations
mentions of defendants in a legal context
New Auto-Interp
Negative Logits
Reichen
-0.76
DebuggerNonUser
-0.75
Roscoe
-0.72
Juf
-0.71
Lande
-0.70
WPS
-0.67
Rote
-0.64
*/
-0.64
ítmény
-0.64
Rolf
-0.64
POSITIVE LOGITS
criminator
0.76
ResponseEntity
0.74
cheibe
0.73
localVar
0.70
Albright
0.69
ENIX
0.68
Pooling
0.68
nexo
0.68
theid
0.68
Beans
0.67
Activations Density 0.632%