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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discipline
    -0.17
    onian
    -0.15
    ofilm
    -0.15
    ODE
    -0.15
    ój
    -0.15
    uben
    -0.14
    ::
    -0.14
    eph
    -0.14
    pletely
    -0.14
    ophile
    -0.14
    POSITIVE LOGITS
    ,params
    0.17
    igkeit
    0.15
    anca
    0.14
    ura
    0.14
    樹
    0.14
    (params
    0.14
    баÑĩ
    0.14
    женÑĮ
    0.14
     modne
    0.14
    OptionsResolver
    0.14
    Act Density 0.011%

    No Known Activations