INDEX
Explanations
mentions of specific names and titles related to individuals
New Auto-Interp
Negative Logits
icari
-0.21
.tie
-0.17
%X
-0.15
chim
-0.15
elenium
-0.15
ollar
-0.15
oux
-0.15
ypi
-0.15
amac
-0.14
nore
-0.14
POSITIVE LOGITS
sson
0.17
-properties
0.14
acen
0.13
.bd
0.13
Brothers
0.13
Aer
0.13
(((
0.13
Issues
0.13
esor
0.13
sposób
0.13
Activations Density 0.111%