INDEX
    Explanations

    Authorization

    New Auto-Interp
    Negative Logits
    LEM
    -0.07
    _counts
    -0.07
     concl
    -0.07
    .IT
    -0.07
    Facet
    -0.07
    _prop
    -0.07
    -0.07
    _piece
    -0.07
    Prop
    -0.07
     pedestrians
    -0.07
    POSITIVE LOGITS
    Bearer
    0.10
     proportional
    0.09
     Unidade
    0.09
     beurre
    0.09
     Boyle
    0.08
     эфир
    0.08
     Beer
    0.08
     óleo
    0.08
     Einheit
    0.08
     очередь
    0.08
    Act Density 0.001%

    No Known Activations