INDEX
Explanations
words and phrases associated with entities that include "Bel."
New Auto-Interp
Negative Logits
%");
-0.57
)");
-0.54
GenerationType
-0.54
%";
-0.52
fuhr
-0.52
]");
-0.51
verletzt
-0.51
FontOfSize
-0.51
"]);
-0.51
جوا
-0.51
POSITIVE LOGITS
Bel
0.80
bel
0.75
Bel
0.73
ris
0.70
bel
0.69
Eth
0.67
Mob
0.65
RIS
0.62
BEL
0.57
belle
0.57
Activations Density 1.980%