INDEX
    Explanations

    dialogue that expresses concern or inquiry about personal well-being and interpersonal relationships

    New Auto-Interp
    Negative Logits
    arkin
    -0.15
     Yong
    -0.15
    ãİ
    -0.15
    esin
    -0.15
    oli
    -0.14
    æ²Ļ
    -0.14
    fos
    -0.14
    pons
    -0.14
    coles
    -0.14
    oyer
    -0.14
    POSITIVE LOGITS
    дав
    0.15
    æ£
    0.14
    ETCH
    0.14
    Interop
    0.14
    606
    0.14
    ÑĦек
    0.14
    IEW
    0.13
    Sequential
    0.13
    ç¯
    0.13
     Gür
    0.13
    Act Density 0.420%

    No Known Activations