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

    Neuronpedia

    INDEX
    Explanations

    mentions of prestigious accolades or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious awards, institutions, or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Phones
    -0.67
    Twe
    -0.65
     Laws
    -0.65
    ter
    -0.64
    eper
    -0.64
    hy
    -0.63
    ogen
    -0.62
    alone
    -0.62
     Bundy
    -0.62
    harm
    -0.62
    POSITIVE LOGITS
     accol
    0.97
     prestigious
    0.96
     honors
    0.90
     awards
    0.90
     adolesc
    0.83
     mosqu
    0.82
     institution
    0.80
     citiz
    0.78
    wcs
    0.76
     satell
    0.76
    Act Density 0.010%

    No Known Activations