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

    Neuronpedia

    INDEX
    Explanations

    mentions of educated individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of education and educated individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aws
    -0.66
    chief
    -0.65
    oter
    -0.64
    coni
    -0.64
    itual
    -0.64
    apa
    -0.63
    itars
    -0.61
    election
    -0.61
    odder
    -0.61
    ascus
    -0.60
    POSITIVE LOGITS
     educated
    1.01
     educ
    0.95
     guesses
    0.92
    educated
    0.90
    ¿½
    0.88
    liter
    0.81
    Educ
    0.79
    llor
    0.77
    uates
    0.76
     upbringing
    0.76
    Act Density 0.022%

    No Known Activations