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

    Neuronpedia

    INDEX
    Explanations

    academic qualifications such as "PhD" and "BA"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of doctoral degrees and related academic credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grounds
    -0.86
    ãĥ«
    -0.73
     Gemini
    -0.73
    ãĥ¼ãĥ³
    -0.69
    ground
    -0.69
    bite
    -0.69
     Peb
    -0.66
     TMZ
    -0.66
    theless
    -0.65
    cars
    -0.65
    POSITIVE LOGITS
     dissertation
    1.16
     thesis
    1.02
    essor
    0.93
    rint
    0.93
     doctoral
    0.92
    uates
    0.88
    ertation
    0.85
    ĨĴ
    0.85
    ysis
    0.82
    iaries
    0.80
    Act Density 0.012%

    No Known Activations