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

    Neuronpedia

    INDEX
    Explanations

    mentions of graduate students

    oai_token-act-pair · gpt-3.5-turbo

    references to graduate education or graduate students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othing
    -0.77
    lam
    -0.74
    ignty
    -0.71
    powers
    -0.67
    iso
    -0.65
    lets
    -0.65
    uin
    -0.64
    amo
    -0.62
    Ñĭ
    -0.62
    âĸĦ
    -0.61
    POSITIVE LOGITS
     graduate
    3.69
     Graduate
    2.26
     graduates
    2.21
    graduate
    2.17
     undergraduate
    2.09
     doctoral
    2.00
     grad
    2.00
     undergrad
    2.00
     graduating
    1.78
     graduated
    1.71
    Act Density 0.016%

    No Known Activations