INDEX
Explanations
mentions of the popular band "Adele."
mentions of the musical artist Adele
New Auto-Interp
Negative Logits
raints
-0.75
raint
-0.74
DPR
-0.72
DERR
-0.70
Papers
-0.68
Kers
-0.66
ulate
-0.66
Izan
-0.65
ossession
-0.63
Kenobi
-0.63
POSITIVE LOGITS
phant
1.29
izabeth
1.05
ghan
1.04
ttes
1.00
venth
0.97
ele
0.96
fter
0.84
ven
0.82
chy
0.81
asure
0.77
Activations Density 0.008%