INDEX
    Explanations

    references to groups or quantities of people or things

    New Auto-Interp
    Negative Logits
    ej
    -0.18
    vara
    -0.16
     McA
    -0.15
     Fever
    -0.14
    ugin
    -0.14
    icas
    -0.14
    ski
    -0.14
    Shield
    -0.14
     +
    -0.13
     Tone
    -0.13
    POSITIVE LOGITS
    ohana
    0.16
    oret
    0.16
    asaki
    0.16
    oretical
    0.15
    icone
    0.15
    roys
    0.15
    /site
    0.14
    į¼
    0.14
    üzel
    0.14
    lick
    0.14
    Act Density 0.278%

    No Known Activations