INDEX
Explanations
terms related to dairy products and their consumption
New Auto-Interp
Negative Logits
asca
-0.16
bs
-0.15
اÙĦ
-0.15
yth
-0.15
ebek
-0.14
_material
-0.14
marriages
-0.14
бин
-0.14
xin
-0.14
marrying
-0.14
POSITIVE LOGITS
lact
0.19
shake
0.18
milk
0.18
aterno
0.16
Byl
0.16
endale
0.15
MOOTH
0.15
erton
0.15
ä¹³
0.15
èĪį
0.15
Activations Density 0.043%