INDEX
Explanations
curly brace characters and their placement
New Auto-Interp
Negative Logits
يتيمه
-0.88
Danger
-0.68
★☆
-0.68
Blatt
-0.67
agog
-0.66
Bene
-0.66
([-
-0.66
مص
-0.66
Danger
-0.66
sé
-0.65
POSITIVE LOGITS
}\
1.66
)\
1.55
)}\
1.42
}}\
1.30
{}\1.29
))\
1.29
})\
1.28
}\
1.27
}}\
1.26
'\
1.23
Activations Density 0.169%