INDEX
Explanations
titles or headings of articles or sections
instances of the phrase "Read more" or similar prompts for further information
New Auto-Interp
Negative Logits
izons
-0.78
aza
-0.69
rette
-0.69
acquaintance
-0.68
gered
-0.66
unda
-0.66
boa
-0.65
subdivision
-0.64
zik
-0.64
arians
-0.63
POSITIVE LOGITS
VIDEOS
0.82
WATCHED
0.80
atican
0.74
Featured
0.72
Recent
0.71
Images
0.71
What
0.70
Why
0.69
TBD
0.68
Photos
0.68
Activations Density 0.070%