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

    Neuronpedia

    INDEX
    Explanations

    references to structural or positional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Star
    -0.63
    Star
    -0.57
    forth
    -0.56
     star
    -0.56
    farb
    -0.55
     hoort
    -0.52
    Tikang
    -0.50
    XPATH
    -0.49
    star
    -0.49
    uparrow
    -0.49
    POSITIVE LOGITS
    MemoryWarning
    0.78
    thâu
    0.77
     ویکی‌پدیای
    0.70
    Tembelea
    0.70
    InSection
    0.69
    Hentet
    0.67
    تقاوى
    0.66
    /**
    0.64
     Italijanski
    0.63
    erialized
    0.62
    Act Density 0.193%

    No Known Activations