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

    Neuronpedia

    INDEX
    Explanations

    professors and their affiliated universities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate academic positions and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.75
     respir
    -0.73
    éĹĺ
    -0.73
     coffin
    -0.71
    proxy
    -0.71
     inval
    -0.70
     activ
    -0.69
     horizont
    -0.67
    ãĤª
    -0.66
     upside
    -0.66
    POSITIVE LOGITS
     Georgetown
    1.44
     NYU
    1.43
     Yale
    1.43
     Rutgers
    1.42
     Princeton
    1.39
     Harvard
    1.39
     Northwestern
    1.38
     Syracuse
    1.34
     Cornell
    1.32
     Dartmouth
    1.31
    Act Density 0.113%

    No Known Activations