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

    Neuronpedia

    INDEX
    Explanations

    mentions of paragraphs and their structure within a document

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

    specific paragraphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BindView
    -0.48
    Lose
    -0.46
     setLoading
    -0.44
    won
    -0.44
    Won
    -0.42
    infec
    -0.41
    Stolen
    -0.41
    Hades
    -0.41
    }`).
    -0.40
    Losing
    -0.40
    POSITIVE LOGITS
     Paragraph
    1.20
     paragraph
    1.20
    Paragraph
    1.20
    paragraph
    1.09
     paragraphs
    1.06
    paragraphs
    0.93
     paragraphe
    0.81
     parag
    0.75
     IndexPath
    0.68
     Parag
    0.68
    Act Density 0.005%

    No Known Activations