INDEX
Explanations
references to justice and injustice in various contexts
New Auto-Interp
Negative Logits
est
-0.50
Przypisy
-0.49
Prime
-0.48
ang
-0.46
Vir
-0.44
Weight
-0.44
брав
-0.44
情况下
-0.43
жит
-0.43
J
-0.43
POSITIVE LOGITS
timestamp
0.95
timestamps
0.82
ComVisible
0.81
judges
0.81
0.79
witnesses
0.78
justice
0.77
/*
0.75
niosek
0.75
//
0.75
Activations Density 0.096%