INDEX
    Explanations

    Names of people

    New Auto-Interp
    Negative Logits
    <bos>
    -0.96
     was
    -0.57
    '
    -0.50
     counted
    -0.48
     is
    -0.48
     received
    -0.46
     reç
    -0.44
     ret
    -0.43
    -0.42
    was
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.83
     يتيمه
    0.72
    Hochspringen
    0.67
    stateProvider
    0.64
    eleste
    0.63
    Referanser
    0.63
     oprot
    0.63
     doPost
    0.63
    versial
    0.63
    utives
    0.63
    Act Density 0.012%

    No Known Activations