INDEX
Explanations
instances of the name "Jane" and variations of it
New Auto-Interp
Negative Logits
gaard
-0.20
yar
-0.19
gings
-0.17
wner
-0.17
edException
-0.16
yonel
-0.16
ะ
-0.15
.LENGTH
-0.15
SHOT
-0.15
gn
-0.15
POSITIVE LOGITS
Aust
0.22
Doe
0.19
en
0.18
bug
0.18
uary
0.18
ust
0.17
ane
0.17
cek
0.16
illo
0.16
cka
0.16
Activations Density 0.006%