INDEX
Explanations
references to distance and the concept of being far away in various contexts
New Auto-Interp
Negative Logits
latter
-0.16
amos
-0.15
ÙĦاÙħ
-0.15
leine
-0.14
atetime
-0.14
ffield
-0.14
anan
-0.14
volta
-0.14
pping
-0.13
mvc
-0.13
POSITIVE LOGITS
غÙĦ
0.15
357
0.15
esture
0.14
iped
0.14
pac
0.14
/end
0.13
distant
0.13
û
0.13
umi
0.13
rum
0.13
Activations Density 0.034%