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

    Neuronpedia

    INDEX
    Explanations

    mentions of academic or professional titles, specifically "associate professor."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    imon
    -0.80
    cale
    -0.77
    ODUCT
    -0.74
    plays
    -0.72
    CRIP
    -0.72
    aneers
    -0.72
    acing
    -0.72
    akens
    -0.72
    =-=-=-=-=-=-=-=-
    -0.71
    itans
    -0.71
    POSITIVE LOGITS
     dean
    1.00
     professor
    0.87
     newsp
    0.83
    lies
    0.80
    lly
    0.79
    rete
    0.72
    ially
    0.69
    rium
    0.68
    ously
    0.68
     colonel
    0.67
    Act Density 0.038%

    No Known Activations