INDEX
Explanations
instructions on different actions related to digital content, such as clicking, toggling, and playing
navigational commands related to editing or viewing content on a webpage
New Auto-Interp
Negative Logits
virginity
-0.72
Ͻ
-0.68
abstinence
-0.67
psychedel
-0.66
Awakening
-0.65
Patriarch
-0.64
affair
-0.64
ethical
-0.64
Galile
-0.62
wagon
-0.62
POSITIVE LOGITS
thumbnail
0.88
captcha
0.87
embed
0.86
CLICK
0.86
iframe
0.85
Click
0.84
click
0.83
click
0.83
URL
0.81
slideshow
0.80
Activations Density 0.296%