INDEX
Explanations
references to actors and actresses in the context of film or television
New Auto-Interp
Negative Logits
beſch
-0.81
vooz
-0.81
müſſen
-0.80
propOrder
-0.79
niſſe
-0.79
majánló
-0.79
ðsíða
-0.79
verſch
-0.77
erſt
-0.76
WithIOException
-0.75
POSITIVE LOGITS
>
0.59
”
0.59
()")
0.53
”
0.52
»
0.50
%',
0.49
>')
0.48
>")
0.47
])]
0.47
%",
0.47
Activations Density 0.538%