INDEX
Explanations
references to specific individuals or institutions in various contexts
New Auto-Interp
Negative Logits
.)}
-0.80
).}
-0.72
propOrder
-0.70
)");
-0.69
$}}
-0.66
kasarigan
-0.66
})$}
-0.64
']],
-0.62
theless
-0.62
[]).
-0.62
POSITIVE LOGITS
—
1.12
—
1.09
selaku
0.98
–
0.94
--
0.91
iaitu
0.82
,
0.79
——
0.79
--
0.78
と呼ばれる
0.77
Activations Density 0.367%