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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of beginnings or starting points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.16
    Oi
    -0.15
    èĴ
    -0.15
    haps
    -0.14
    лаб
    -0.14
     preparedStatement
    -0.13
    opak
    -0.13
    ÐľÐŀ
    -0.13
    cape
    -0.13
     ÐĹд
    -0.13
    POSITIVE LOGITS
    affen
    0.17
    antom
    0.16
    oming
    0.15
    atti
    0.15
    /end
    0.14
    éļĨ
    0.14
    /top
    0.14
     Bou
    0.14
    nings
    0.13
     Mej
    0.13
    Act Density 0.026%

    No Known Activations