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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to various categories and subjects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    thumbnails
    -0.84
     lawy
    -0.83
     summ
    -0.77
     plur
    -0.75
     bonded
    -0.75
     subcontract
    -0.73
     reinvent
    -0.73
     facilit
    -0.72
     Cosponsors
    -0.71
     hiber
    -0.71
    POSITIVE LOGITS
     Carbuncle
    0.79
    azz
    0.77
    daq
    0.77
    uncture
    0.74
    oran
    0.72
    throw
    0.72
     xx
    0.71
     Decker
    0.71
     Anon
    0.71
    essee
    0.70
    Act Density 12.850%

    No Known Activations