INDEX
Explanations
references to social media platforms, particularly Facebook
New Auto-Interp
Negative Logits
etak
-0.18
Foley
-0.18
rief
-0.15
ORTH
-0.15
Downloads
-0.14
Birch
-0.14
ogui
-0.14
875
-0.14
owo
-0.14
citas
-0.14
POSITIVE LOGITS
0.23
0.20
0.19
fb
0.19
0.19
0.17
acebook
0.17
Rai
0.16
pinned
0.16
fb
0.15
Activations Density 0.049%