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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Zero
    -0.07
    一封
    -0.07
    Eastern
    -0.07
    场比赛
    -0.07
    (mock
    -0.07
    .GetHashCode
    -0.07
     nothing
    -0.07
    党总
    -0.07
     删除
    -0.07
    ()?
    -0.07
    POSITIVE LOGITS
     명
    0.07
     ينب
    0.07
    bot
    0.07
    קומ
    0.07
    ʃ
    0.07
     conditioner
    0.06
     федер
    0.06
    ệnh
    0.06
    失调
    0.06
    규
    0.06
    Act Density 0.003%

    No Known Activations