INDEX
Explanations
words related to bananas, such as 'banana' itself or phrases containing 'banana'
references to bananas
New Auto-Interp
Negative Logits
Ö¼
-0.91
tml
-0.79
Cosponsors
-0.79
pter
-0.76
sing
-0.74
å§«
-0.72
ROR
-0.72
enegger
-0.71
yll
-0.71
nces
-0.71
POSITIVE LOGITS
banana
1.05
bananas
1.04
peel
0.97
pudding
0.86
carrot
0.83
pancakes
0.83
fruit
0.80
toast
0.79
juice
0.78
beetles
0.77
Activations Density 0.004%