INDEX
Explanations
non-verbal whitespace or special characters in the text
New Auto-Interp
Negative Logits
.",
-0.85
Hone
-0.82
.";
-0.79
'
-0.78
Kenne
-0.78
...',
-0.76
KTP
-0.76
.'.
-0.75
Pozri
-0.75
JpaRepository
-0.75
POSITIVE LOGITS
1.42
1.38
)
1.30
.
1.20
$
1.18
,
1.09
}$
1.01
:
0.99
-
0.95
0.85
Activations Density 0.330%