INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    arquia
    -0.75
    surname
    -0.73
    Conse
    -0.73
     Gravel
    -0.71
    disp
    -0.71
     많
    -0.71
     fruto
    -0.70
    reda
    -0.70
    issier
    -0.70
    そこから
    -0.69
    POSITIVE LOGITS
     plates
    1.60
     plate
    1.34
    plates
    1.27
     Plates
    1.26
     Plate
    1.23
    plate
    1.19
    Plate
    1.18
     Eurasian
    1.15
     PLATES
    1.13
     PLATE
    1.06
    Act Density 0.014%

    No Known Activations