INDEX
    Explanations

    exclamatory and interrogative punctuation indicating strong emotions

    New Auto-Interp
    Negative Logits
    ãģįãģŁ
    -0.18
    akin
    -0.16
    ial
    -0.15
    ëį°
    -0.15
    inya
    -0.15
     nÃło
    -0.15
    .githubusercontent
    -0.14
    orious
    -0.14
    /or
    -0.14
    othy
    -0.14
    POSITIVE LOGITS
    cluded
    0.16
    oker
    0.16
    Ø©
    0.16
    ERIC
    0.14
    è¯Ŀ
    0.14
    oted
    0.14
    obble
    0.14
    anine
    0.14
     latter
    0.14
    ery
    0.14
    Act Density 0.113%

    No Known Activations