INDEX
Explanations
mentions of specific food items with a focus on salads
New Auto-Interp
Negative Logits
ledged
-0.84
founded
-0.83
auer
-0.76
oho
-0.72
closed
-0.70
sten
-0.70
fram
-0.70
urrencies
-0.69
IBLE
-0.69
wu
-0.68
POSITIVE LOGITS
dressing
1.07
dress
1.04
greens
0.96
waitress
0.91
Dress
0.86
salad
0.79
gown
0.79
dresses
0.77
bowl
0.77
garden
0.77
Activations Density 0.032%