INDEX
Explanations
roles and contributions related to various processes or relationships
New Auto-Interp
Negative Logits
enerbahçe
-0.48
bieber
-0.48
िया
-0.47
enerbah
-0.47
éril
-0.45
druge
-0.44
ensalada
-0.44
Esperanto
-0.43
志
-0.43
materna
-0.42
POSITIVE LOGITS
sizeCache
1.15
ModelExpression
1.13
role
0.99
Role
0.96
esternos
0.96
محفوظة
0.90
Role
0.88
الإنجليزية
0.85
role
0.85
ThroughAttribute
0.85
Activations Density 0.429%