INDEX
Explanations
references to artwork and paintings
references to paintings or artwork
New Auto-Interp
Negative Logits
DN
-0.90
nir
-0.75
aucus
-0.73
ularity
-0.71
ornia
-0.71
SN
-0.69
reek
-0.68
ãĥĥãĥī
-0.68
aspx
-0.66
ulin
-0.66
POSITIVE LOGITS
paintings
1.19
painter
1.16
depicting
1.11
artwork
1.05
painting
0.98
portraits
0.93
art
0.93
Painting
0.89
ysc
0.87
mural
0.85
Activations Density 0.045%