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

    Neuronpedia

    INDEX
    Explanations

    professor titles and affiliated universities

    oai_token-act-pair · gpt-3.5-turbo

    affiliations to academic institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    200000
    -0.71
     wagon
    -0.68
    0000000000000000
    -0.67
    ãĤª
    -0.67
     kneeling
    -0.67
    âĶ
    -0.66
     upside
    -0.66
    xual
    -0.65
     proxies
    -0.65
    Accessory
    -0.65
    POSITIVE LOGITS
     NYU
    1.55
     Harvard
    1.52
     Yale
    1.47
     Cornell
    1.47
     University
    1.46
     Rutgers
    1.46
     Stanford
    1.43
     Princeton
    1.43
     Carnegie
    1.43
     UCLA
    1.41
    Act Density 0.112%

    No Known Activations