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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Stationary
    0.38
    MRS
    0.37
    知
    0.37
    に通
    0.36
    oulos
    0.36
    مرة
    0.36
    embrie
    0.35
     AT
    0.35
    esth
    0.35
     stationary
    0.35
    POSITIVE LOGITS
    Lea
    0.46
     Lea
    0.41
    粳
    0.39
     Dickens
    0.39
    biid
    0.38
    釭
    0.37
     ሂ
    0.37
    숯
    0.36
    バラ
    0.36
     вікі
    0.36
    Act Density 0.001%

    No Known Activations