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

    Neuronpedia

    INDEX
    Explanations

    sections related to definitions and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.92
    WriteBarrier
    -0.92
     betweenstory
    -0.86
    DeleteBehavior
    -0.77
    Eksteraj
    -0.76
    MemoryWarning
    -0.75
     Италијани
    -0.75
     kasarigan
    -0.74
     ComVisible
    -0.73
     ویکی‌پدی
    -0.73
    POSITIVE LOGITS
     igjen
    0.48
     again
    0.47
     weer
    0.47
    tif
    0.46
    Alas
    0.45
     dry
    0.43
    </strong>
    0.43
    ಷ್
    0.42
     without
    0.41
    bach
    0.41
    Act Density 0.359%

    No Known Activations