INDEX
Explanations
references to a specific entity, "Dor"
occurrences of the name "Dor."
New Auto-Interp
Negative Logits
anwhile
-0.95
WAYS
-0.75
unct
-0.65
HS
-0.64
Terrorism
-0.64
)=(
-0.63
BRE
-0.63
tenance
-0.62
eers
-0.62
³³³³³³³³
-0.61
POSITIVE LOGITS
ado
0.99
iane
0.98
ÃŃa
0.97
je
0.93
oshenko
0.89
cas
0.89
omial
0.87
rell
0.87
chester
0.87
acies
0.87
Activations Density 0.012%