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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    igil
    -0.84
    eryl
    -0.84
    agic
    -0.83
    iture
    -0.79
    odied
    -0.77
    isdom
    -0.75
    atche
    -0.74
    agy
    -0.72
    elsius
    -0.72
    perty
    -0.71
    POSITIVE LOGITS
     sexes
    0.84
     genders
    0.79
     moderators
    0.79
     embargo
    0.69
     fences
    0.66
     moder
    0.65
    cgi
    0.63
    wcsstore
    0.62
     protocols
    0.62
    geries
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.