INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     &
    -3.02
    &
    -2.02
     \&
    -1.61
    ,&
    -1.50
     (&
    -1.48
    (&
    -1.43
    )&
    -1.30
    }&
    -1.29
     &,
    -1.28
    -1.26
    POSITIVE LOGITS
    amp
    0.88
    ndash
    0.86
    mdash
    0.82
     greateſt
    0.79
    quot
    0.78
     ſtre
    0.77
     purpoſe
    0.77
    קישורים
    0.77
     ſeveral
    0.76
     ſtate
    0.75
    Act Density 0.053%

    No Known Activations