INDEX
Explanations
ingredients and food-related terms in recipes
New Auto-Interp
Negative Logits
ValueStyle
-0.77
ChildScrollView
-0.60
transQ
-0.59
הערות
-0.57
TestTools
-0.56
الحياه
-0.54
PerformLayout
-0.54
GraphicsUnit
-0.53
+#+
-0.53
__':
-0.52
POSITIVE LOGITS
tramonto
0.50
partidas
0.47
povo
0.46
invitaciones
0.46
roxo
0.42
campañas
0.41
mostaza
0.40
morado
0.40
argli
0.40
cucchia
0.40
Activations Density 1.062%