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

    Neuronpedia

    INDEX
    Explanations

    terms related to configuration and management policies within a structured system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orianCalendar
    -0.91
    Javadoc
    -0.83
    BeginContext
    -0.83
    thâu
    -0.79
    LookAnd
    -0.74
     חיצוניים
    -0.73
     الحره
    -0.73
    TagMode
    -0.73
    RegistryLite
    -0.72
     GenerationType
    -0.72
    POSITIVE LOGITS
     prof
    0.43
    ↵↵
    0.40
    le
    0.40
     vVar
    0.39
    oldo
    0.39
    .
    0.39
    langkah
    0.39
     simp
    0.38
     conversation
    0.38
    Compar
    0.38
    Act Density 0.700%

    No Known Activations