INDEX
Explanations
mentions of soy products
New Auto-Interp
Negative Logits
*/(
-0.85
CBI
-0.77
hani
-0.76
Imran
-0.71
Rove
-0.66
Humanity
-0.65
Anonymous
-0.64
Ic
-0.64
Alexandria
-0.62
Learned
-0.62
POSITIVE LOGITS
beans
1.72
bean
1.71
food
1.03
bowl
0.92
seed
0.88
beans
0.88
lda
0.88
sauce
0.86
char
0.86
wh
0.84
Activations Density 0.002%