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

    Neuronpedia

    INDEX
    Explanations

    academic terminology related to education and training in a specific field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Psychol
    -0.55
    Initiative
    -0.54
     initiative
    -0.53
     Initiative
    -0.52
    הערות
    -0.46
     Holl
    -0.46
    generational
    -0.46
    ellow
    -0.44
    ']
    -0.44
     re
    -0.44
    POSITIVE LOGITS
     chapter
    0.68
    MemoryWarning
    0.67
    basic
    0.65
     فريبيس
    0.65
     básicos
    0.64
     Topics
    0.64
    本章
    0.63
     LECTURE
    0.63
     Lecture
    0.62
     básico
    0.62
    Act Density 0.217%

    No Known Activations