INDEX
Explanations
the word "again" and its variations
New Auto-Interp
Negative Logits
kano
-0.81
Hern
-0.68
ZI
-0.65
o
-0.64
Koc
-0.63
Hale
-0.63
fect
-0.62
fers
-0.61
Purdy
-0.61
отношению
-0.61
POSITIVE LOGITS
again
1.73
Again
1.71
again
1.69
Again
1.66
AGAIN
1.60
AGAIN
1.48
igjen
1.27
novamente
1.17
Lagi
1.08
nuevamente
1.07
Activations Density 0.047%