INDEX
Explanations
expressions conveying emotions or personal thoughts
instances of the phrase "I feel like."
New Auto-Interp
Negative Logits
alt
-0.80
hiba
-0.75
earance
-0.75
ircraft
-0.75
arling
-0.72
bard
-0.69
abases
-0.69
afa
-0.66
omen
-0.65
als
-0.65
POSITIVE LOGITS
crap
0.80
shit
0.75
dé
0.68
lier
0.68
parity
0.67
slipping
0.67
spitting
0.67
jumping
0.65
lihood
0.65
pulling
0.64
Activations Density 0.023%