INDEX
Explanations
indicators of content publication and online engagement metrics
New Auto-Interp
Negative Logits
banner
-0.17
-
-0.16
368
-0.16
-
-0.16
Dit
-0.15
Ver
-0.15
"
-0.15
uma
-0.14
Banner
-0.14
âĢ
-0.14
POSITIVE LOGITS
ekler
0.19
aeper
0.17
#ga
0.16
upert
0.15
ITIZE
0.15
tae
0.15
ourd
0.15
ÐĬ
0.15
ipple
0.14
-*-č↵
0.14
Activations Density 0.022%