INDEX
Explanations
instances of food-related products or ingredients
New Auto-Interp
Negative Logits
ç¥ĸ
-0.15
fulness
-0.15
esty
-0.14
emet
-0.14
emes
-0.14
odesk
-0.14
elsing
-0.14
emap
-0.14
Moore
-0.14
_MAP
-0.14
POSITIVE LOGITS
-shaped
0.20
-bordered
0.17
inct
0.17
èά
0.16
beiter
0.15
ECTOR
0.15
-sized
0.15
sized
0.15
shaped
0.15
syndrome
0.15
Activations Density 0.283%