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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    osuke
    -0.86
    reciation
    -0.83
    ogly
    -0.77
    crew
    -0.75
    idon
    -0.73
    olding
    -0.73
    od
    -0.71
    bryce
    -0.71
    ome
    -0.69
    build
    -0.66
    POSITIVE LOGITS
     decriminal
    0.72
     polio
    0.67
     rall
    0.66
     proced
    0.66
     redistributed
    0.63
    waters
    0.63
     mete
    0.62
     metast
    0.62
    uria
    0.62
     persecut
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.