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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    akeru
    -0.82
    ilogy
    -0.76
     Lerner
    -0.65
    onse
    -0.65
    washer
    -0.64
    idis
    -0.63
    igan
    -0.63
     Lambert
    -0.62
     Marathon
    -0.62
    demon
    -0.61
    POSITIVE LOGITS
    vo
    0.73
    EMBER
    0.70
    ossier
    0.69
    eways
    0.67
     Quantity
    0.63
     minerals
    0.61
     Bots
    0.61
    emouth
    0.60
    chn
    0.60
    Ver
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.