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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uthor
    -0.82
    opsis
    -0.79
    padding
    -0.77
    mercial
    -0.76
    inventoryQuantity
    -0.75
     thous
    -0.75
    Iterator
    -0.74
    icter
    -0.70
    priv
    -0.68
    adic
    -0.68
    POSITIVE LOGITS
    ington
    0.68
     Canterbury
    0.64
    bra
    0.63
     Devil
    0.63
     Quest
    0.62
    heimer
    0.61
     Bottom
    0.61
    hall
    0.60
     Tigers
    0.60
    Ö¼
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.