INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     clap
    -0.06
    Lots
    -0.06
    γκό
    -0.06
    resolved
    -0.06
     just
    -0.06
    ational
    -0.06
    én
    -0.06
    unting
    -0.06
     Crist
    -0.06
    etermin
    -0.06
    POSITIVE LOGITS
    Furthermore
    0.07
     furthermore
    0.07
     ProductService
    0.07
    -chair
    0.06
     moreover
    0.06
    0.06
     kamu
    0.06
    Narrated
    0.06
     Saf
    0.06
    Nov
    0.06
    Act Density 0.015%

    No Known Activations