INDEX
Explanations
references to privacy policies and data security issues related to WhatsApp
New Auto-Interp
Negative Logits
undi
-0.18
odial
-0.15
Emails
-0.14
pa
-0.14
oren
-0.14
ty
-0.14
Moy
-0.14
lassen
-0.14
_SO
-0.14
acular
-0.14
POSITIVE LOGITS
Bot
0.23
bot
0.23
Bot
0.23
bot
0.22
-bot
0.21
.Bot
0.20
tg
0.20
bots
0.19
Telegram
0.19
.bot
0.19
Activations Density 0.013%