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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    我省
    -0.07
    azole
    -0.07
     dance
    -0.07
    Larry
    -0.07
     stro
    -0.07
     thỏ
    -0.07
     tight
    -0.06
    麋
    -0.06
    ancial
    -0.06
    白色
    -0.06
    POSITIVE LOGITS
    ULATE
    0.07
     replicated
    0.07
    _est
    0.07
    .override
    0.07
     couleur
    0.07
    衠
    0.07
    閱
    0.06
    	valid
    0.06
    聞いた
    0.06
     Chat
    0.06
    Act Density 0.006%

    No Known Activations