INDEX
Explanations
mentions or references to the country "Costa Rica"
references to Costa Rica
New Auto-Interp
Negative Logits
ittens
-0.78
ROR
-0.77
umbn
-0.73
ashed
-0.73
CLE
-0.70
erness
-0.69
selves
-0.68
skirts
-0.68
ellen
-0.65
acular
-0.65
POSITIVE LOGITS
Rica
1.53
Rican
1.24
Costa
1.20
icum
0.86
Mesa
0.82
Diego
0.78
Brav
0.73
zeb
0.72
ÃŃa
0.71
endish
0.71
Activations Density 0.005%