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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbered paragraphs in legal or formal documents

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

    section references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }`).
    -0.43
    won
    -0.43
    killed
    -0.42
    Lose
    -0.41
    invit
    -0.40
    due
    -0.40
    Abel
    -0.40
     unstable
    -0.39
    abe
    -0.39
     fates
    -0.39
    POSITIVE LOGITS
     paragraph
    2.22
     Paragraph
    2.09
    Paragraph
    2.09
    paragraph
    2.00
     paragraphs
    1.89
    paragraphs
    1.63
     paragraphe
    1.42
     parag
    1.15
    parag
    1.01
     Parag
    0.95
    Act Density 0.002%

    No Known Activations