INDEX
Explanations
references to rock music
references to rock music and related themes
New Auto-Interp
Negative Logits
ufact
-0.91
rha
-0.71
xus
-0.69
ilities
-0.68
chio
-0.66
ples
-0.66
oresc
-0.66
ienced
-0.65
iencies
-0.64
URES
-0.63
POSITIVE LOGITS
castle
1.01
ers
0.96
stars
0.91
stead
0.90
er
0.89
birds
0.84
papers
0.79
away
0.79
climbers
0.77
ford
0.77
Activations Density 0.016%