INDEX
Explanations
mentions of the name "Craig."
New Auto-Interp
Negative Logits
MBER
-0.17
erde
-0.17
ombine
-0.16
erals
-0.16
qus
-0.16
ibling
-0.15
åı·
-0.15
hek
-0.15
ToOne
-0.14
eck
-0.14
POSITIVE LOGITS
ures
0.19
ie
0.18
sm
0.17
head
0.17
sville
0.17
y
0.17
ler
0.16
quot
0.16
ory
0.16
head
0.16
Activations Density 0.027%