INDEX
Explanations
the company name "Nestlé"
mentions of specific brands and companies
New Auto-Interp
Negative Logits
istically
-0.80
ACTIONS
-0.71
Weasley
-0.70
Ń·
-0.70
WAYS
-0.69
++++++++++++++++
-0.67
fare
-0.67
ajor
-0.67
ãģĦ
-0.67
plane
-0.65
POSITIVE LOGITS
lé
1.25
orius
1.10
Nest
1.03
ea
1.00
eus
0.89
orians
0.86
eas
0.84
actory
0.82
unia
0.81
ensibly
0.81
Activations Density 0.021%