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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lished
    -0.69
     Athletic
    -0.65
    """
    -0.62
     Secrets
    -0.61
     Labyrinth
    -0.60
    soDeliveryDate
    -0.60
     please
    -0.59
    =>
    -0.58
    gas
    -0.58
     transports
    -0.57
    POSITIVE LOGITS
    inn
    2.08
    iken
    0.84
    row
    0.80
    aeda
    0.76
    ãĥ¼ãĥĨ
    0.73
    icken
    0.71
    IELD
    0.70
    izzle
    0.70
    ileaks
    0.69
    illard
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.