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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Inferno
    -0.68
     cru
    -0.66
     Purg
    -0.64
     favoured
    -0.62
     yarn
    -0.62
    urated
    -0.61
     Queens
    -0.61
     ports
    -0.61
     bombers
    -0.61
     Tanks
    -0.60
    POSITIVE LOGITS
    eanor
    0.73
    Thumbnail
    0.73
    igure
    0.73
    insula
    0.73
    entary
    0.72
    ansky
    0.71
    utive
    0.69
    """
    0.69
    udeb
    0.68
    Offline
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.