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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical processes and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.15
    ürn
    -0.14
     soci
    -0.14
    bbe
    -0.14
     Temper
    -0.14
     firm
    -0.14
    _Callback
    -0.13
    arent
    -0.13
    поÑĩ
    -0.13
    \<^
    -0.13
    POSITIVE LOGITS
    iren
    0.16
    veau
    0.15
    оба
    0.14
     Pok
    0.14
    pag
    0.14
    ulk
    0.14
    leon
    0.14
    doll
    0.13
    undry
    0.13
    à¥Ģतर
    0.13
    Act Density 0.017%

    No Known Activations