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

    Neuronpedia

    INDEX
    Explanations

    words related to education and learning

    oai_token-act-pair · gpt-3.5-turbo

    references to courses or educational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mented
    -0.70
    alty
    -0.69
     curtain
    -0.64
    phant
    -0.63
    thening
    -0.61
    arijuana
    -0.61
    idespread
    -0.60
    Mini
    -0.59
     stake
    -0.59
    axy
    -0.58
    POSITIVE LOGITS
    course
    1.00
    washer
    0.92
    Course
    0.91
    ourses
    0.87
    books
    0.85
     Course
    0.80
     courses
    0.78
    work
    0.77
    meal
    0.76
    ibur
    0.76
    Act Density 0.029%

    No Known Activations