INDEX
Explanations
phrases related to subscriptions or sign-up attempts
phrases related to subscription issues and errors
New Auto-Interp
Negative Logits
bush
-0.83
utic
-0.72
facts
-0.68
finding
-0.67
factor
-0.66
wagon
-0.66
forth
-0.64
uesday
-0.63
fman
-0.63
hend
-0.62
POSITIVE LOGITS
iframe
0.70
intrusive
0.63
socks
0.62
Gutenberg
0.62
Optional
0.61
esi
0.61
embed
0.61
WRITE
0.59
HTML
0.58
javascript
0.58
Activations Density 0.028%