INDEX
Explanations
references to fruit
mentions of fruit
New Auto-Interp
Negative Logits
DOS
-0.68
Govern
-0.67
aution
-0.66
kson
-0.66
ategory
-0.66
entric
-0.66
agonists
-0.66
orld
-0.65
FINE
-0.64
Govern
-0.63
POSITIVE LOGITS
fruit
1.24
fruit
1.09
cake
1.06
juice
1.05
fruits
0.97
cakes
0.94
ruit
0.87
fulness
0.84
nect
0.83
juices
0.79
Activations Density 0.019%