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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sofar
    -0.73
    icka
    -0.66
    iana
    -0.65
    pointer
    -0.64
    efficient
    -0.63
     Patterson
    -0.63
    ryce
    -0.63
    ierre
    -0.63
    cko
    -0.62
    inition
    -0.60
    POSITIVE LOGITS
    ONES
    0.79
    itters
    0.69
    anz
    0.66
    د
    0.63
     negro
    0.61
    owship
    0.61
     odds
    0.60
    ãĥĨãĤ£
    0.60
    ãĤ¡
    0.60
    BUR
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.