INDEX
Explanations
mentions of the word "Costa."
mentions of "Costa Rica."
New Auto-Interp
Negative Logits
ngth
-0.84
selves
-0.76
erness
-0.76
acular
-0.76
ROR
-0.75
umbn
-0.71
oppable
-0.70
lihood
-0.70
perse
-0.69
race
-0.68
POSITIVE LOGITS
Rica
1.64
Rican
1.42
Costa
0.90
Mesa
0.82
icum
0.81
Brav
0.77
ð
0.73
etti
0.71
beans
0.71
Cru
0.70
Activations Density 0.014%