INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ſame
    -0.65
     ſaid
    -0.64
     ſub
    -0.60
     ſhe
    -0.59
     Houſe
    -0.58
     ſen
    -0.58
     beſt
    -0.58
     poffe
    -0.57
     ſtand
    -0.57
    $_.
    -0.57
    POSITIVE LOGITS
     as
    0.82
    interopRequire
    0.60
     Например
    0.60
     např
    0.54
    }}_{\
    0.54
    ंदीखरीदारी
    0.54
     bijvoorbeeld
    0.54
    as
    0.53
    InsertCommand
    0.53
    NOPQRST
    0.52
    Act Density 0.084%

    No Known Activations