INDEX
Explanations
references to food-related establishments and their products
New Auto-Interp
Negative Logits
y
-0.20
agar
-0.17
ernals
-0.16
erno
-0.16
mtree
-0.16
sink
-0.15
yb
-0.15
ennen
-0.15
iard
-0.15
vore
-0.15
POSITIVE LOGITS
bing
0.26
fusc
0.24
bed
0.24
ility
0.23
lique
0.22
stacle
0.21
berman
0.21
ILITY
0.20
acteria
0.19
bers
0.19
Activations Density 0.027%