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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    amment
    -0.07
     Dann
    -0.07
    uese
    -0.07
    考核
    -0.07
    _SYMBOL
    -0.07
    ール
    -0.07
     Pour
    -0.07
    ]));
    -0.06
    还没有
    -0.06
    unities
    -0.06
    POSITIVE LOGITS
    ofs
    0.07
    bru
    0.07
    rika
    0.07
     anarchist
    0.07
    ńska
    0.06
    רוך
    0.06
     ayrı
    0.06
    刑警
    0.06
     fray
    0.06
    𫍲
    0.06
    Act Density 0.009%

    No Known Activations