INDEX
Explanations
phrases related to the food item "Caesar salad."
references to Caesar salad or variations of the term "caesar."
New Auto-Interp
Negative Logits
olve
-0.69
justice
-0.65
andom
-0.65
anted
-0.65
story
-0.63
ighter
-0.63
matter
-0.61
gotten
-0.60
PLAY
-0.60
olves
-0.58
POSITIVE LOGITS
ca
3.86
Ca
1.52
ca
1.32
Ca
1.22
CA
1.17
cu
1.05
caut
1.01
Cu
0.99
CA
0.98
caul
0.97
Activations Density 0.013%