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

    Neuronpedia

    INDEX
    Explanations

    references to academic degrees or educational qualifications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.74
    gm
    -0.70
    arna
    -0.69
    iders
    -0.66
     Samson
    -0.66
    miah
    -0.65
    BY
    -0.64
    itans
    -0.63
     Iter
    -0.62
    sels
    -0.61
    POSITIVE LOGITS
     conferred
    1.06
    ploma
    1.03
     awarded
    0.93
     degrees
    0.90
     Degree
    0.88
     degree
    0.87
    ertation
    0.87
     dissertation
    0.85
     Celsius
    0.83
    rees
    0.83
    Act Density 0.031%

    No Known Activations