INDEX
Explanations
references to cooking methods and the state of food being prepared
New Auto-Interp
Negative Logits
idas
-0.79
venants
-0.72
umbn
-0.71
ertodd
-0.70
ortium
-0.69
xus
-0.67
operator
-0.66
rium
-0.65
dfx
-0.64
guiActiveUn
-0.64
POSITIVE LOGITS
rice
0.88
meats
0.86
stove
0.86
stall
0.83
Cook
0.81
spaghetti
0.80
cooks
0.80
meat
0.80
aste
0.80
cooked
0.79
Activations Density 0.008%