INDEX
Explanations
words indicating a sense of disappointment or emotional distress
New Auto-Interp
Negative Logits
onga
-0.17
vida
-0.16
ha
-0.15
ailable
-0.15
cid
-0.15
POSIT
-0.15
aired
-0.14
воз
-0.14
anness
-0.14
ende
-0.14
POSITIVE LOGITS
concert
0.19
pir
0.18
yll
0.18
heart
0.18
array
0.18
quiet
0.18
ses
0.17
rray
0.17
Grace
0.17
son
0.16
Activations Density 0.015%