INDEX
Explanations
references to emotional or psychological distress
New Auto-Interp
Negative Logits
Scully
-0.69
tein
-0.65
ipedia
-0.65
istration
-0.65
hetti
-0.63
llan
-0.63
agall
-0.62
ioch
-0.62
lane
-0.61
usha
-0.61
POSITIVE LOGITS
distress
1.11
ingly
1.04
otions
0.83
rained
0.78
phia
0.75
ances
0.74
raints
0.70
ACTIONS
0.70
OUS
0.69
disturbance
0.69
Activations Density 0.007%