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

    Neuronpedia

    INDEX
    Explanations

    references to academic education levels, particularly graduate programs and students

    oai_token-act-pair · gpt-3.5-turbo

    references to graduate and undergraduate students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.80
    rw
    -0.73
    eger
    -0.72
    hare
    -0.72
     Shack
    -0.68
     constitu
    -0.67
    Ö¼
    -0.66
    hed
    -0.65
    ality
    -0.64
    pload
    -0.64
    POSITIVE LOGITS
     student
    0.89
    uates
    0.85
    student
    0.80
     Student
    0.79
     tuition
    0.78
     students
    0.78
    interstitial
    0.78
    iate
    0.76
     dissertation
    0.75
    uations
    0.74
    Act Density 0.012%

    No Known Activations