INDEX
    Explanations

    conversational interactions and expressions of gratitude

    New Auto-Interp
    Negative Logits
    ish
    -0.14
    _EXTENSIONS
    -0.14
    adr
    -0.13
    ses
    -0.13
    Æ¡
    -0.13
     ÎŃν
    -0.13
    \CMS
    -0.13
    atri
    -0.13
    anz
    -0.13
    æĮĻ
    -0.13
    POSITIVE LOGITS
     thanks
    0.94
     thank
    0.93
     Thanks
    0.85
    thanks
    0.80
    Thanks
    0.79
     Thank
    0.79
     THANK
    0.74
    thank
    0.73
    Thank
    0.72
     thanked
    0.68
    Act Density 0.048%

    No Known Activations