INDEX
Explanations
mentions of the name "Doug" and its variations
New Auto-Interp
Negative Logits
er
-0.16
/us
-0.15
antha
-0.15
llx
-0.15
ersed
-0.14
uong
-0.14
θÏħ
-0.14
icens
-0.14
eyn
-0.14
ر
-0.13
POSITIVE LOGITS
ships
0.17
ued
0.15
ustin
0.14
wel
0.14
جاد
0.14
ils
0.14
doc
0.14
worthy
0.13
anto
0.13
site
0.13
Activations Density 0.004%