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

    Neuronpedia

    INDEX
    Explanations

    special characters used to denote sections or highlights in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ШÐIJ
    -0.15
    UpInside
    -0.15
    ạng
    -0.15
     Halk
    -0.15
    ilst
    -0.15
    Ñĩай
    -0.14
    ysi
    -0.14
    using
    -0.13
    говоÑĢ
    -0.13
     bychom
    -0.13
    POSITIVE LOGITS
    ï¸ı
    0.17
    ever
    0.14
    AYER
    0.14
    ĺ
    0.14
     Stewart
    0.13
     gob
    0.13
     diligence
    0.13
     else
    0.13
    ssi
    0.13
    xFFFFFFFF
    0.13
    Act Density 0.014%

    No Known Activations