INDEX
    Explanations

    expressions of gratitude and acknowledgment

    New Auto-Interp
    Negative Logits
    оÑĢод
    -0.14
    û
    -0.13
     taj
    -0.13
    æĹıèĩªæ²»
    -0.13
    oler
    -0.13
     гоÑĤ
    -0.13
    tooltip
    -0.12
     Authority
    -0.12
    umm
    -0.12
    _hook
    -0.12
    POSITIVE LOGITS
     thank
    0.77
     thanks
    0.69
     Thank
    0.68
     THANK
    0.66
     Thanks
    0.64
    Thank
    0.62
    thank
    0.61
    thanks
    0.59
    Thanks
    0.59
     gracias
    0.56
    Act Density 0.351%

    No Known Activations