INDEX
Explanations
first names
mentions of the name "Karl."
New Auto-Interp
Negative Logits
LV
-0.68
Called
-0.66
flix
-0.66
nder
-0.66
NX
-0.65
ndra
-0.64
FFER
-0.64
Dangerous
-0.62
vide
-0.59
MAKE
-0.58
POSITIVE LOGITS
owship
1.12
anguage
1.08
ounge
1.00
ophone
0.99
atan
0.94
oths
0.94
owe
0.93
ottesville
0.93
ength
0.93
ibrary
0.89
Activations Density 0.028%