INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
    atiek
    -0.08
     นี้
    -0.08
    uity
    -0.08
    /design
    -0.07
    873
    -0.07
    edas
    -0.07
     vaš
    -0.07
    allero
    -0.07
    Proposal
    -0.07
    POSITIVE LOGITS
     individuales
    0.09
     individuele
    0.08
     individuelle
    0.08
    _spacing
    0.08
     convict
    0.08
     individual
    0.07
     spacing
    0.07
     einzelne
    0.07
     afzonder
    0.07
     Eti
    0.07
    Act Density 0.050%

    No Known Activations