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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    stocks
    -0.83
    buster
    -0.72
     evid
    -0.70
    endment
    -0.69
     receivers
    -0.68
     inventory
    -0.65
    catentry
    -0.64
     remission
    -0.64
    laughter
    -0.64
    busters
    -0.63
    POSITIVE LOGITS
    essional
    0.76
    achy
    0.74
    lected
    0.71
     Forgotten
    0.71
    ached
    0.66
     Tanz
    0.64
    anche
    0.64
    idable
    0.63
     forthcoming
    0.62
    mentioned
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.