INDEX
Explanations
social media platform names
social media platform names
New Auto-Interp
Negative Logits
xual
-0.74
weld
-0.72
appar
-0.69
footing
-0.68
hement
-0.65
ewitness
-0.65
asymm
-0.65
unaccount
-0.65
manif
-0.63
principle
-0.63
POSITIVE LOGITS
Tumblr
0.99
Interstitial
0.97
0.88
0.87
0.86
sharing
0.81
0.81
Trend
0.81
Share
0.78
0.78
Activations Density 0.076%