INDEX
Explanations
mentions of the name "Lee."
New Auto-Interp
Negative Logits
st
-0.22
dür
-0.16
stations
-0.16
yu
-0.15
neau
-0.15
riad
-0.15
же
-0.15
most
-0.15
ll
-0.15
memberOf
-0.14
POSITIVE LOGITS
uw
0.26
Roy
0.23
Ann
0.23
ann
0.22
bove
0.21
bron
0.20
ce
0.20
lee
0.19
anne
0.19
Ann
0.18
Activations Density 0.007%