INDEX
Explanations
interactions and engagement actions related to social media, particularly Facebook
New Auto-Interp
Negative Logits
ostel
-0.16
Bhar
-0.16
adr
-0.15
åĬ
-0.15
ssel
-0.15
ervo
-0.14
uben
-0.14
sWith
-0.14
ä¹ī
-0.14
ernet
-0.14
POSITIVE LOGITS
Disposition
0.15
opi
0.14
éĢł
0.14
ÑĢен
0.14
itos
0.13
hv
0.13
ihn
0.13
trand
0.13
ullan
0.13
atti
0.13
Activations Density 0.029%