INDEX
Explanations
quotes or references to notable individuals
New Auto-Interp
Negative Logits
seau
-0.17
azzi
-0.17
ázi
-0.16
$MESS
-0.15
hibit
-0.15
rote
-0.15
nox
-0.15
ebi
-0.14
avir
-0.14
chein
-0.14
POSITIVE LOGITS
ourke
0.20
Conor
0.20
Irish
0.19
ullivan
0.16
788
0.16
Shea
0.16
Mahon
0.16
Carthy
0.15
_simps
0.15
Brady
0.14
Activations Density 0.028%