INDEX
Explanations
references to Africa and its various aspects
New Auto-Interp
Negative Logits
yyyy
-0.65
deal
-0.63
mi
-0.62
rest
-0.62
处
-0.61
Domenico
-0.57
cele
-0.57
ゆ
-0.56
Loh
-0.56
mie
-0.56
POSITIVE LOGITS
Africa
1.40
Africans
1.31
afric
1.30
AFRICA
1.30
África
1.29
Africa
1.29
africa
1.25
africa
1.24
africains
1.21
africano
1.18
Activations Density 0.066%