INDEX
Explanations
mentions of the name "Chris."
New Auto-Interp
Negative Logits
ONA
-0.19
hift
-0.16
uled
-0.16
ebb
-0.16
ç§
-0.16
erv
-0.15
viso
-0.15
492
-0.15
rost
-0.15
(CultureInfo
-0.14
POSITIVE LOGITS
opher
0.32
itian
0.27
itan
0.25
ophe
0.22
elda
0.21
óst
0.20
elle
0.18
ensen
0.18
anth
0.17
elles
0.17
Activations Density 0.012%