INDEX
Explanations
features related to kitchens and dining areas in homes
New Auto-Interp
Negative Logits
-0.17
oline
-0.16
e
-0.15
ãģ¾ãģĻ
-0.15
iqu
-0.14
ust
-0.14
558
-0.14
gle
-0.14
644
-0.14
Asc
-0.14
POSITIVE LOGITS
ctr
0.17
precation
0.16
ruba
0.16
iot
0.15
lectron
0.15
iten
0.15
akis
0.15
èįĴ
0.15
etwork
0.15
avn
0.15
Activations Density 0.026%