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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Anniversary
    -0.70
     Ples
    -0.68
    anooga
    -0.67
     moderators
    -0.66
    olitics
    -0.65
     Myr
    -0.64
     fixme
    -0.64
    resy
    -0.63
    cest
    -0.63
     Myst
    -0.63
    POSITIVE LOGITS
    netflix
    0.67
    oan
    0.64
    phabet
    0.64
    ovi
    0.62
    duct
    0.62
    olean
    0.61
    etooth
    0.61
    layer
    0.60
    umpy
    0.60
    benefit
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.