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

    Neuronpedia

    INDEX
    Explanations

    coding-related terms and operations involving buffers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odel
    -0.18
    abra
    -0.15
     Dion
    -0.14
    523
    -0.14
    eker
    -0.14
    strup
    -0.14
     Datum
    -0.14
    моÑĤ
    -0.14
     ward
    -0.14
    agh
    -0.14
    POSITIVE LOGITS
     Vk
    0.27
     vk
    0.27
    KHR
    0.26
     device
    0.26
     Vulkan
    0.25
    vk
    0.24
     Device
    0.24
     Pipeline
    0.23
     VK
    0.23
    ulkan
    0.23
    Act Density 0.008%

    No Known Activations