INDEX
    Explanations

    articles and determiners in the text

    New Auto-Interp
    Negative Logits
    utan
    -0.15
    assy
    -0.14
    leine
    -0.14
    ensis
    -0.14
    er
    -0.14
       
    -0.14
    zd
    -0.14
    ir
    -0.13
    ihan
    -0.13
    ses
    -0.13
    POSITIVE LOGITS
    iaux
    0.17
    sand
    0.15
     birthdays
    0.15
    NamedQuery
    0.14
    -envelope
    0.14
     consequence
    0.14
    BufferData
    0.13
     pÅĻipom
    0.13
     Teil
    0.13
    702
    0.13
    Act Density 0.021%

    No Known Activations