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

    Neuronpedia

    INDEX
    Explanations

    academic terms and course-related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.73
    mented
    -0.68
     stake
    -0.68
    phant
    -0.68
     curtain
    -0.63
    rises
    -0.61
    arijuana
    -0.61
    usalem
    -0.58
    hap
    -0.58
     territ
    -0.58
    POSITIVE LOGITS
    course
    1.04
    Course
    0.97
    washer
    0.93
    ourses
    0.92
     Course
    0.87
    books
    0.86
     courses
    0.81
    meal
    0.78
     instructors
    0.78
    ibur
    0.77
    Act Density 0.025%

    No Known Activations