INDEX
Explanations
mentions of the name "Bill."
New Auto-Interp
Negative Logits
esso
-0.19
yne
-0.17
cool
-0.15
eling
-0.14
eed
-0.14
ept
-0.14
ists
-0.14
.GroupLayout
-0.14
elling
-0.14
ector
-0.14
POSITIVE LOGITS
iards
0.31
iard
0.30
boards
0.29
ows
0.24
ions
0.24
ings
0.23
board
0.22
owy
0.21
ingham
0.20
owing
0.20
Activations Density 0.013%