INDEX
    Explanations

    punctuation marks, specifically periods

    New Auto-Interp
    Negative Logits
     blonde
    -0.15
    ãģĵãģ¡ãĤī
    -0.14
    uw
    -0.14
    VIOUS
    -0.14
    _OVERRIDE
    -0.14
    styled
    -0.13
    üre
    -0.13
    İY
    -0.13
     små
    -0.13
    ady
    -0.13
    POSITIVE LOGITS
    hift
    0.16
    Ïĥμ
    0.16
    lig
    0.15
    efined
    0.15
    liest
    0.14
    rog
    0.14
    kan
    0.14
    ocker
    0.14
    ät
    0.13
    plib
    0.13
    Act Density 0.017%

    No Known Activations