INDEX
Explanations
possessive forms indicating ownership or association
New Auto-Interp
Negative Logits
ainfi
-0.66
ientras
-0.66
pecabe
-0.65
myſelf
-0.57
ambién
-0.57
vább
-0.55
Wikiseite
-0.53
-0.53
defaultstate
-0.52
itſelf
-0.52
POSITIVE LOGITS
s
0.75
his
0.68
His
0.67
their
0.66
Your
0.61
your
0.61
Their
0.60
own
0.59
My
0.58
His
0.57
Activations Density 0.248%