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

    Neuronpedia

    INDEX
    Explanations

    strings that represent configuration settings or attribute values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.15
    ucas
    -0.15
    isclosed
    -0.14
    лиÑĪком
    -0.14
    eor
    -0.14
    orgia
    -0.14
    rysler
    -0.13
    edi
    -0.13
    ifton
    -0.13
    ilm
    -0.13
    POSITIVE LOGITS
    ÂĿ
    0.14
    anker
    0.14
    [@
    0.14
    enny
    0.14
    à¸Ľà¸ı
    0.14
    urement
    0.14
    ogany
    0.14
     href
    0.13
    antry
    0.13
    ANGED
    0.13
    Act Density 0.066%

    No Known Activations