INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    iddel
    -0.09
    ubble
    -0.09
    ’H
    -0.08
    idding
    -0.08
    'H
    -0.08
    adii
    -0.07
    -0.07
    elschap
    -0.07
     LAD
    -0.07
     protegido
    -0.07
    POSITIVE LOGITS
     prov
    0.10
     ber
    0.08
     Jac
    0.08
     meest
    0.08
     etiam
    0.08
    (((
    0.07
    {\
    0.07
    0.07
     television
    0.07
     totale
    0.07
    Act Density 0.006%

    No Known Activations