INDEX
Explanations
mentions of the name "Brad."
New Auto-Interp
Negative Logits
embr
-0.15
agnostics
-0.15
åij½
-0.15
iw
-0.15
.fi
-0.15
esson
-0.15
dust
-0.14
chwitz
-0.14
ared
-0.14
nez
-0.14
POSITIVE LOGITS
ley
0.31
shaw
0.28
ford
0.28
LEY
0.27
leys
0.25
en
0.24
bury
0.24
enton
0.24
enburg
0.19
street
0.19
Activations Density 0.007%