INDEX
Explanations
YouTube video links
references to YouTube links and videos
New Auto-Interp
Negative Logits
luster
-0.71
Dull
-0.62
essler
-0.62
Ballard
-0.60
bilateral
-0.59
Gibbs
-0.59
Palo
-0.58
Greenberg
-0.57
lust
-0.57
Kitt
-0.57
POSITIVE LOGITS
youtu
1.02
youtube
0.93
ĸļ
0.90
watch
0.76
Ö
0.73
:/
0.71
plays
0.70
WATCHED
0.70
uration
0.69
acknow
0.69
Activations Density 0.014%