Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    硌
    -0.08
    !")
    -0.07
    _dropout
    -0.07
    ']))↵↵
    -0.07
    获得感
    -0.07
    %%%
    -0.07
    unny
    -0.07
    赌场
    -0.07
    tant
    -0.07
    ꂫ
    -0.06
    POSITIVE LOGITS
    特殊
    0.07
     equality
    0.07
     vriend
    0.07
     sprzę
    0.07
     を
    0.07
     Rel
    0.06
     Control
    0.06
     erotici
    0.06
    援助
    0.06
     musicians
    0.06
    Act Density 0.004%

    No Known Activations