INDEX
    Explanations

    specific names such as "Burkman" or "Dillman"

    mentions of specific individuals or teams

    New Auto-Interp
    Negative Logits
    AMI
    -0.78
    ebook
    -0.77
     Popular
    -0.76
    displayText
    -0.72
    nels
    -0.71
    schild
    -0.70
    lain
    -0.68
    anamo
    -0.68
    tumblr
    -0.66
    eering
    -0.66
    POSITIVE LOGITS
     lettuce
    0.88
    hovah
    0.88
    alo
    0.87
    ¿½
    0.85
    ivery
    0.85
    ¶ħ
    0.84
    ©¶æ¥µ
    0.83
    estinal
    0.83
    ¾
    0.81
     cabbage
    0.80
    Act Density 0.021%

    No Known Activations