INDEX
Explanations
the presence of specific prepositions and definite articles
New Auto-Interp
Negative Logits
Faso
-0.74
Spek
-0.73
Squal
-0.73
Togo
-0.71
Myra
-0.70
pâtes
-0.70
QL
-0.69
Sochi
-0.69
Medea
-0.67
jiga
-0.65
POSITIVE LOGITS
∗
1.22
"):
1.00
'):
0.97
'));
0.86
']);
0.79
'),
0.79
');
0.78
):
0.77
]);
0.77
])
0.75
Activations Density 0.000%