INDEX
Explanations
phrases indicating emotional or psychological distress
New Auto-Interp
Negative Logits
dál
-0.15
azzi
-0.15
ibern
-0.15
.nasa
-0.15
rita
-0.14
_keeper
-0.14
azy
-0.14
ùi
-0.14
ActionCreators
-0.14
Destructor
-0.14
POSITIVE LOGITS
spontaneously
0.16
SPD
0.14
spontaneous
0.14
anten
0.14
l
0.14
cap
0.13
etto
0.13
uffs
0.13
738
0.13
ido
0.13
Activations Density 0.000%