INDEX
    Explanations

    interactions involving requests or questions directed at individuals

    New Auto-Interp
    Negative Logits
    oola
    -0.16
    viso
    -0.15
    orget
    -0.15
    asmus
    -0.15
    uve
    -0.15
    oky
    -0.15
    imers
    -0.15
    abble
    -0.14
    ece
    -0.14
    ฤ
    -0.14
    POSITIVE LOGITS
     questions
    0.32
     whether
    0.32
     about
    0.31
     why
    0.31
     how
    0.29
     what
    0.26
     Questions
    0.24
    why
    0.23
    whether
    0.23
    questions
    0.23
    Act Density 0.037%

    No Known Activations