INDEX
Explanations
emotions or sensations
expressions of emotional experiences
New Auto-Interp
Negative Logits
abo
-0.68
entitle
-0.66
inter
-0.63
pend
-0.62
Mans
-0.62
IPO
-0.61
clusive
-0.60
frog
-0.58
include
-0.58
ono
-0.57
POSITIVE LOGITS
felt
3.39
feels
2.28
felt
2.24
feel
2.08
feel
1.87
regretted
1.66
feeling
1.63
sensed
1.60
smelled
1.58
tasted
1.54
Activations Density 0.016%