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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Oval
    -0.78
    "]=>
    -0.75
     Mens
    -0.69
    enged
    -0.63
    stown
    -0.63
    eways
    -0.62
     Myth
    -0.62
     War
    -0.61
    verse
    -0.60
    wcs
    -0.60
    POSITIVE LOGITS
     *.
    0.71
    endas
    0.68
    omez
    0.66
    cards
    0.62
    iculty
    0.61
     Gong
    0.61
     pulse
    0.61
    rence
    0.60
    boat
    0.60
    ERO
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.