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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     acquaintance
    -0.69
    Ģ
    -0.68
    enhagen
    -0.65
    interstitial
    -0.65
    idy
    -0.63
     Ajax
    -0.63
    aciously
    -0.62
    ittance
    -0.61
    nce
    -0.61
    ibur
    -0.61
    POSITIVE LOGITS
    ertodd
    0.73
     Notting
    0.67
     Extrem
    0.65
     Gaia
    0.65
     Lauder
    0.64
    efer
    0.62
    oom
    0.62
     Thatcher
    0.61
    FIN
    0.60
     Peak
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.