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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     생명
    -0.07
    茱
    -0.07
    拤
    -0.07
    قود
    -0.06
    百年
    -0.06
    uos
    -0.06
    [left
    -0.06
    钯
    -0.06
    辟
    -0.06
     trumpet
    -0.06
    POSITIVE LOGITS
    akhir
    0.07
     merged
    0.07
    abo
    0.07
    Billing
    0.07
    _coverage
    0.07
    Yeah
    0.07
    Which
    0.07
    枅
    0.06
     absol
    0.06
    想要
    0.06
    Act Density 0.002%

    No Known Activations