INDEX
Explanations
mentions of researchers and their credentials or affiliations
New Auto-Interp
Negative Logits
iterals
-0.16
žÃŃ
-0.16
à¹Ĩ
-0.15
Slut
-0.15
.annotate
-0.15
Ñīи
-0.15
Įĵ
-0.14
ergy
-0.14
rvine
-0.14
yonel
-0.14
POSITIVE LOGITS
Archae
0.20
archae
0.19
archaeological
0.18
indiv
0.16
paste
0.15
virtual
0.15
n
0.15
Paleo
0.15
arch
0.15
contra
0.15
Activations Density 0.035%