INDEX
Explanations
references to photo captions
mentions of photographs and visual content
New Auto-Interp
Negative Logits
ministic
-0.76
merce
-0.74
hattan
-0.67
mington
-0.62
stood
-0.62
foreseeable
-0.61
ancial
-0.61
Hutchinson
-0.60
blot
-0.60
sembly
-0.57
POSITIVE LOGITS
Caption
0.84
Gallery
0.73
Photos
0.72
ource
0.71
Photos
0.67
ets
0.65
ynthesis
0.65
ensitive
0.64
س
0.63
Amount
0.62
Activations Density 0.010%