INDEX
    Explanations

    names of people or characters from specific contexts

    New Auto-Interp
    Negative Logits
    sheet
    -0.91
    sheets
    -0.91
    otle
    -0.76
    boro
    -0.71
     Madden
    -0.71
    orge
    -0.70
    MO
    -0.70
    ophon
    -0.68
     Deck
    -0.68
    ounters
    -0.68
    POSITIVE LOGITS
    ikuman
    0.93
    alyses
    0.79
    qua
    0.78
    jiang
    0.78
    ctive
    0.77
    ascus
    0.75
    cture
    0.75
    ishment
    0.73
    ctions
    0.73
    cheon
    0.73
    Act Density 0.035%

    No Known Activations