INDEX
Explanations
references to a weight loss supplement or product
New Auto-Interp
Negative Logits
ooke
-0.15
oyer
-0.14
má
-0.14
vyk
-0.14
rok
-0.14
rollo
-0.14
lom
-0.14
uids
-0.13
rego
-0.13
775
-0.13
POSITIVE LOGITS
istrovstvÃŃ
0.19
Garc
0.16
COMPUTER
0.15
Morgan
0.15
ningar
0.14
à¤
0.14
Bauer
0.14
cardio
0.14
||(
0.14
Norris
0.14
Activations Density 0.000%