INDEX
Explanations
names of individuals in various contexts
New Auto-Interp
Negative Logits
bout
-0.15
adays
-0.15
W
-0.15
akit
-0.15
odore
-0.14
es
-0.14
shock
-0.14
an
-0.14
A
-0.13
both
-0.13
POSITIVE LOGITS
jang
0.17
ioxide
0.14
BoundingClientRect
0.14
dü
0.14
nea
0.14
ANNOT
0.14
lesi
0.14
psilon
0.14
Ŀi
0.14
ibel
0.14
Activations Density 0.213%