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

    Neuronpedia

    INDEX
    Explanations

    references to sections in a document

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

    section role or identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.53
    <em>
    -0.38
    interopRequire
    -0.37
     lie
    -0.35
    Did
    -0.32
    Lie
    -0.31
    <h3>
    -0.31
     Betriebs
    -0.30
    </h3>
    -0.29
     Maloney
    -0.29
    POSITIVE LOGITS
    section
    1.61
    sections
    1.08
     section
    1.00
     sections
    0.95
    InSection
    0.90
     Section
    0.88
    Section
    0.87
    SECTION
    0.86
     Sections
    0.85
    sectional
    0.84
    Act Density 0.003%

    No Known Activations