INDEX
    Explanations

    mentions of specific names, particularly "Tyler" and other individuals

    New Auto-Interp
    Negative Logits
    ร
    -0.18
    oir
    -0.16
    viron
    -0.16
    QUARE
    -0.15
    uter
    -0.15
    ย
    -0.15
    _planes
    -0.14
     clo
    -0.14
    disposing
    -0.14
    åİħ
    -0.14
    POSITIVE LOGITS
    éĥİ
    0.18
    ITES
    0.16
     kadar
    0.15
    emic
    0.15
    bourne
    0.15
    ian
    0.15
    plorer
    0.14
    strar
    0.14
    ãģĦãģŁ
    0.14
    mania
    0.14
    Act Density 0.116%

    No Known Activations