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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    peed
    -0.79
    atorium
    -0.78
    wolves
    -0.77
    erc
    -0.75
    atism
    -0.71
    emed
    -0.69
    pee
    -0.68
    cells
    -0.67
    ears
    -0.65
    keyes
    -0.65
    POSITIVE LOGITS
     Gap
    0.76
    èĪ
    0.75
     McKenzie
    0.75
     Moff
    0.74
     Nish
    0.71
     Clancy
    0.70
     McKin
    0.70
     Debor
    0.69
     Bernstein
    0.67
    ãĥ¼ãĥĨãĤ£
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.