INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     praise
    -0.07
     panor
    -0.07
    -0.07
    🌁
    -0.07
    gift
    -0.07
     phase
    -0.07
    kontakte
    -0.07
     node
    -0.07
    lient
    -0.06
     days
    -0.06
    POSITIVE LOGITS
    _FLOAT
    0.07
    cms
    0.07
    0.07
    =text
    0.07
    _imag
    0.07
    Lint
    0.06
    isma
    0.06
     Lessons
    0.06
    ằng
    0.06
     Citation
    0.06
    Act Density 0.048%

    No Known Activations