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

    Neuronpedia

    INDEX
    Explanations

    specific formatting and structural elements in documents or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dieux
    -0.67
     justiça
    -0.67
     rêves
    -0.63
     courants
    -0.62
     enfance
    -0.61
     générations
    -0.60
     manquer
    -0.60
    […]
    -0.58
     AssemblyCompany
    -0.58
     entonces
    -0.58
    POSITIVE LOGITS
    RectangleBorder
    0.76
     Vý
    0.73
     Prze
    0.65
    ſelves
    0.65
     mdi
    0.64
    Пере
    0.64
     inſ
    0.64
    За
    0.64
     OBD
    0.63
    CppCodeGen
    0.63
    Act Density 0.046%

    No Known Activations