INDEX
Explanations
images or phrases related to images
references to images in the text
New Auto-Interp
Negative Logits
cffff
-0.90
aptic
-0.84
hurst
-0.84
ategory
-0.83
itte
-0.82
ighter
-0.78
uckle
-0.78
woods
-0.76
kson
-0.76
odcast
-0.75
POSITIVE LOGITS
galleries
0.98
gallery
0.96
gallery
0.93
caption
0.88
images
0.86
img
0.84
macros
0.84
image
0.81
Gallery
0.78
depicting
0.78
Activations Density 0.040%