INDEX
Explanations
Facebook-related content
mentions of Facebook and social media interactions
New Auto-Interp
Negative Logits
nces
-0.96
zin
-0.69
ursed
-0.65
odied
-0.65
inence
-0.64
vette
-0.63
toe
-0.63
Overt
-0.62
cephal
-0.62
aneous
-0.62
POSITIVE LOGITS
Messenger
0.95
nect
0.82
username
0.79
0.79
0.76
Username
0.74
icus
0.73
0.72
acebook
0.71
username
0.71
Activations Density 0.019%