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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acock
    -0.07
    oleon
    -0.07
    醛
    -0.06
    鲮
    -0.06
    Commercial
    -0.06
    months
    -0.06
     Bordeaux
    -0.06
    ']}↵
    -0.06
     VALID
    -0.06
     boiled
    -0.06
    POSITIVE LOGITS
     가치
    0.07
     mz
    0.06
    不下
    0.06
    ();//
    0.06
    的习惯
    0.06
     Attention
    0.06
    _unregister
    0.06
    _DISABLE
    0.06
    -platform
    0.06
    带来了
    0.06
    Act Density 0.012%

    No Known Activations