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

    Neuronpedia

    INDEX
    Explanations

    references to elements and components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustin
    -0.18
    coming
    -0.17
     çĻº
    -0.17
     nghiá»ĩm
    -0.16
    icker
    -0.16
    orta
    -0.16
    ãģ¾ãģŁ
    -0.15
    bone
    -0.15
    gow
    -0.15
    silver
    -0.15
    POSITIVE LOGITS
    alist
    0.26
    ized
    0.24
    ials
    0.22
    ial
    0.22
    /component
    0.20
    ially
    0.20
    fault
    0.19
    ally
    0.19
    IAL
    0.19
    wise
    0.18
    Act Density 0.115%

    No Known Activations