INDEX
    Explanations

    themes of hypocrisy and social critique

    New Auto-Interp
    Negative Logits
    eel
    -0.16
    ë³µ
    -0.15
    (æ°´
    -0.15
    thy
    -0.14
    onda
    -0.14
    eln
    -0.14
    ovy
    -0.14
    oug
    -0.14
    heiro
    -0.14
    หลวà¸ĩ
    -0.13
    POSITIVE LOGITS
     Äijá»ĭnh
    0.15
    angstrom
    0.14
     psych
    0.14
    اسÙĬ
    0.14
     Spit
    0.14
    né
    0.13
    ãģĿãģ®
    0.13
    ãĥ¼ãĥį
    0.13
     Bod
    0.13
     Temper
    0.13
    Act Density 0.032%

    No Known Activations