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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of curiosity about people's preferences and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veau
    -0.19
    orge
    -0.15
     DependencyProperty
    -0.15
    ioc
    -0.15
    ernet
    -0.14
    ģµ
    -0.14
     Bernardino
    -0.14
    NG
    -0.14
    abbage
    -0.14
    urch
    -0.13
    POSITIVE LOGITS
    аниÑĨ
    0.16
    ìĬ¹
    0.15
    ick
    0.15
    AUSE
    0.14
    745
    0.14
     MVP
    0.14
    zeit
    0.14
    ami
    0.14
    stell
    0.14
    лаÑĢа
    0.14
    Act Density 0.035%

    No Known Activations