INDEX
Explanations
references to a specific character or name within various contexts
New Auto-Interp
Negative Logits
lidene
-0.73
doubtnut
-0.64
Aryan
-0.62
་་
-0.61
autorytatywna
-0.61
Chham
-0.60
Suz
-0.60
buckwheat
-0.59
PDR
-0.58
يميديا
-0.58
POSITIVE LOGITS
kor
1.05
kor
0.95
Kor
0.95
COR
0.93
Cur
0.93
Cor
0.92
Cor
0.90
cur
0.90
Kor
0.90
COR
0.90
Activations Density 3.091%