INDEX
Explanations
terms related to legal or moral obligations
references to obligations or responsibilities commonly described as "duty."
New Auto-Interp
Negative Logits
ergy
-0.72
vae
-0.69
anz
-0.67
Juliet
-0.67
Lans
-0.66
Iter
-0.65
quart
-0.65
ogene
-0.64
corn
-0.64
Tate
-0.63
POSITIVE LOGITS
Duty
1.02
duty
1.01
duty
0.99
uty
0.98
station
0.77
guiActiveUn
0.74
owed
0.74
refres
0.72
ful
0.72
illet
0.71
Activations Density 0.019%