INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     obituary
    -0.08
     syndicated
    -0.08
     ouvi
    -0.08
    .pet
    -0.08
    xor
    -0.08
    'époque
    -0.07
    -0.07
    -0.07
     undead
    -0.07
     Porte
    -0.07
    POSITIVE LOGITS
     axis
    0.10
     valign
    0.09
     axes
    0.09
     Axis
    0.09
    Axis
    0.09
    .axis
    0.09
    -axis
    0.09
    0.09
    axis
    0.08
     grup
    0.08
    Act Density 0.002%

    No Known Activations