INDEX
Explanations
labels and captions for images or posts
sections with document navigational elements and metadata information
New Auto-Interp
Negative Logits
Palest
-0.75
Sparrow
-0.63
rower
-0.61
omore
-0.59
gem
-0.57
oret
-0.57
schild
-0.56
stead
-0.55
Cyborg
-0.55
stre
-0.55
POSITIVE LOGITS
guiActiveUnfocused
1.04
Quote
0.91
Submit
0.87
Thumbnails
0.87
»
0.86
Download
0.86
IMAGES
0.84
Loading
0.84
Tweet
0.82
Hide
0.82
Activations Density 0.206%