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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ufe
    -0.07
    doğan
    -0.07
     locate
    -0.07
     Вас
    -0.07
    mage
    -0.06
     ре
    -0.06
    当年
    -0.06
    ものが
    -0.06
    .thread
    -0.06
     tốc
    -0.06
    POSITIVE LOGITS
    ])]↵
    0.07
    ">-->↵
    0.07
    ")]
↵
    0.07
     Hib
    0.07
    "],
↵
    0.07
     collective
    0.07
     HOLDER
    0.07
    ]")]↵
    0.06
    列
    0.06
     outliers
    0.06
    Act Density 0.001%

    No Known Activations