INDEX
    Explanations

    negations and expressions of disappointment or failure

    New Auto-Interp
    Negative Logits
    agar
    -0.16
    ©
    -0.16
    uly
    -0.15
     ÑĩеÑģÑĤÑĮ
    -0.14
    ily
    -0.14
    quo
    -0.14
    haled
    -0.14
    hea
    -0.14
    ungi
    -0.13
     grosse
    -0.13
    POSITIVE LOGITS
     sod
    0.16
    411
    0.15
     McMahon
    0.15
    ogle
    0.14
    936
    0.14
    ساب
    0.13
    δα
    0.13
    atorial
    0.13
    767
    0.13
    563
    0.13
    Act Density 0.089%

    No Known Activations