INDEX
Explanations
instances of the name "Christopher"
New Auto-Interp
Negative Logits
cores
-0.18
.scalablytyped
-0.17
viso
-0.17
achuset
-0.17
ombok
-0.15
.Paths
-0.15
COPE
-0.15
ifier
-0.14
unate
-0.14
unds
-0.14
POSITIVE LOGITS
Columbus
0.24
Robin
0.20
colum
0.18
os
0.17
Nolan
0.17
Ree
0.15
opher
0.14
Robin
0.14
Disease
0.14
mee
0.14
Activations Density 0.007%