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

    Neuronpedia

    INDEX
    Explanations

    words related to graduate studies or education

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "graduates" and related academic terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underrated
    -0.64
    iesta
    -0.61
     NASL
    -0.61
    ITE
    -0.60
     Bigfoot
    -0.59
     crew
    -0.59
     rightfully
    -0.59
     believe
    -0.59
     seized
    -0.58
     Description
    -0.58
    POSITIVE LOGITS
    grad
    4.79
    graduate
    2.65
    Grad
    2.19
     Grad
    1.87
    gradation
    1.70
    grade
    1.55
    grades
    1.46
     grad
    1.42
    grading
    1.30
    gradient
    1.28
    Act Density 0.012%

    No Known Activations