INDEX
Explanations
references to Facebook and its related operations or features
New Auto-Interp
Negative Logits
iod
-0.85
atche
-0.83
aterasu
-0.83
rice
-0.80
hiro
-0.78
turtle
-0.77
éŃĶ
-0.76
belt
-0.76
Ces
-0.76
tar
-0.75
POSITIVE LOGITS
2.20
Zuckerberg
2.00
1.84
1.67
FB
1.66
1.64
Snapchat
1.51
1.51
1.48
FB
1.28
Activations Density 0.339%