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

    Neuronpedia

    INDEX
    Explanations

    references to entertainment or movie-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ham
    -0.19
    ham
    -0.16
    stead
    -0.15
     Ham
    -0.15
    HAM
    -0.15
    ÑĮÑİÑĤ
    -0.15
    ãģĮåĩº
    -0.15
    edii
    -0.14
    amarin
    -0.14
    brace
    -0.14
    POSITIVE LOGITS
    isma
    0.16
    rag
    0.15
    彩票
    0.15
    丶
    0.15
    374
    0.15
    nel
    0.14
     sake
    0.14
    ĸ
    0.14
    fcn
    0.14
     purposes
    0.14
    Act Density 0.047%

    No Known Activations