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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bish
    -0.71
    arthed
    -0.70
     sacrific
    -0.69
     unemploy
    -0.68
    itism
    -0.68
    ulously
    -0.67
     resil
    -0.67
    itative
    -0.66
    iter
    -0.65
    lier
    -0.64
    POSITIVE LOGITS
    inki
    0.78
    rawdownloadcloneembedreportprint
    0.74
    PN
    0.73
    mac
    0.66
    windows
    0.63
    externalActionCode
    0.62
    early
    0.62
     Engel
    0.61
    wind
    0.59
     Burr
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.