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

    Neuronpedia

    INDEX
    Explanations

    references to examples and citations in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allis
    -0.17
    IDGET
    -0.17
    l
    -0.15
    adia
    -0.14
    505
    -0.14
    ola
    -0.14
     .
    -0.14
    rug
    -0.14
    iew
    -0.14
    anc
    -0.14
    POSITIVE LOGITS
    ï¸ı
    0.18
    957
    0.14
    illisecond
    0.14
    953
    0.14
    skins
    0.14
    auses
    0.14
    QueryString
    0.14
    .ta
    0.14
    een
    0.14
    orgia
    0.14
    Act Density 0.013%

    No Known Activations