INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     advocate
    -0.08
    ointments
    -0.08
     earthquake
    -0.08
     osp
    -0.08
     advocacy
    -0.08
     potens
    -0.08
     proc
    -0.08
    áz
    -0.08
    Women
    -0.07
    Validator
    -0.07
    POSITIVE LOGITS
     koffie
    0.08
     Alltag
    0.08
     Initialize
    0.08
     처음
    0.08
     belge
    0.08
     коф
    0.08
     swirling
    0.07
    itele
    0.07
    0.07
     Chem
    0.07
    Act Density 0.001%

    No Known Activations