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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ulla
    -0.72
    hots
    -0.71
    erey
    -0.71
    resy
    -0.69
    Preview
    -0.67
    haw
    -0.66
     Oro
    -0.65
    Common
    -0.64
    BIL
    -0.64
     Booker
    -0.63
    POSITIVE LOGITS
    employment
    0.67
     empires
    0.63
    shit
    0.62
     punch
    0.61
    hook
    0.61
     empowerment
    0.61
     EN
    0.60
    ryce
    0.60
    luster
    0.59
    uminati
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.