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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Noir
    -0.07
    [X
    -0.07
    製作
    -0.07
    ī
    -0.07
     Sax
    -0.07
    dzi
    -0.07
     Maple
    -0.06
    IPH
    -0.06
     Junk
    -0.06
    >I
    -0.06
    POSITIVE LOGITS
    攥
    0.08
    手感
    0.07
    perse
    0.07
     KNOW
    0.07
    ꡔ
    0.07
     validates
    0.07
     kcal
    0.07
    .GetFiles
    0.07
    Ze
    0.07
    ...)↵↵
    0.06
    Act Density 0.013%

    No Known Activations