INDEX
Explanations
instances of dialogue with character actions and descriptions
references to protected classes and discrimination issues
New Auto-Interp
Negative Logits
guiName
-0.67
":[{"-0.67
onga
-0.63
ãĢIJ
-0.60
ãĢİ
-0.58
agnetic
-0.57
FTWARE
-0.55
commod
-0.52
adverse
-0.52
osponsors
-0.51
POSITIVE LOGITS
.)
1.88
.)
1.87
!)
1.76
âĢ¦)
1.76
?)
1.75
.):
1.74
*)
1.73
.),
1.73
.).
1.70
...)
1.69
Activations Density 0.398%