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

    Neuronpedia

    INDEX
    Explanations

    terms related to scoring systems and point allocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mate
    -0.17
    pta
    -0.17
    argo
    -0.14
    pData
    -0.14
    ungalow
    -0.13
    izo
    -0.13
    orners
    -0.13
    aths
    -0.13
    pdata
    -0.13
     IService
    -0.13
    POSITIVE LOGITS
    logan
    0.15
    Biz
    0.14
    orney
    0.14
    ushman
    0.14
    наÑĩе
    0.14
    fort
    0.13
     seni
    0.13
     Cru
    0.13
    Cy
    0.13
    ory
    0.13
    Act Density 0.073%

    No Known Activations