INDEX
Explanations
references to individuals with the title "Sir."
New Auto-Interp
Negative Logits
edo
-0.20
kili
-0.17
ncia
-0.17
esan
-0.17
enheim
-0.17
mr
-0.17
_ABI
-0.16
ekt
-0.16
eurs
-0.16
avian
-0.15
POSITIVE LOGITS
ikit
0.20
ius
0.19
leaf
0.19
rah
0.17
ach
0.17
اکÛĮ
0.17
lo
0.17
iously
0.17
acha
0.16
isha
0.16
Activations Density 0.012%