INDEX
Explanations
social media platform mentions, with a strong focus on Facebook
references to social media platforms and calls to follow or connect with accounts
New Auto-Interp
Negative Logits
cise
-0.59
awoken
-0.56
transpl
-0.55
ersen
-0.55
rans
-0.55
plurality
-0.55
©¶æ
-0.54
rue
-0.54
indign
-0.54
ighed
-0.54
POSITIVE LOGITS
HERE
0.91
edin
0.81
âĸº
0.78
@
0.77
0.75
(@
0.75
PAGE
0.72
page
0.72
www
0.71
Follow
0.70
Activations Density 0.060%