INDEX
Explanations
proper names of individuals, particularly surnames
names or initials of individuals
New Auto-Interp
Negative Logits
Rebirth
-0.77
··
-0.67
Transparency
-0.65
vanity
-0.63
browsing
-0.60
Tsuk
-0.59
constant
-0.59
Respect
-0.59
fragmented
-0.59
loyal
-0.59
POSITIVE LOGITS
aney
1.21
adden
1.21
antz
1.17
ansky
1.08
ittle
1.08
iman
1.08
alter
1.07
ough
1.06
auer
1.06
annon
1.05
Activations Density 0.077%