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

    Neuronpedia

    INDEX
    Explanations

    references to specific sections or subsections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Referring to a specific Section

    np_acts-logits-general · gemini-2.0-flash

    section marker or reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagLayout
    -0.73
     Theſe
    -0.71
    ]--;
    -0.69
     estekak
    -0.69
     hab
    -0.66
    onade
    -0.66
     Oliven
    -0.66
     Diſ
    -0.64
    Vem
    -0.64
    🏻
    -0.64
    POSITIVE LOGITS
     SECTION
    1.40
     Sections
    1.39
    Sections
    1.37
     section
    1.37
    SECTION
    1.36
     sections
    1.36
     Section
    1.35
     SECTIONS
    1.29
    Section
    1.29
    section
    1.14
    Act Density 0.155%

    No Known Activations