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

    Neuronpedia

    INDEX
    Explanations

    text related to news articles and content, possibly focusing on specific sections or paragraphs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    sentences that make claims or statements, often beginning with phrases like "We think", "How we see", "You'll notice", or "I am a firm believer".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @eekay

    Transitional phrases that connect ideas or introduce new information in text, often at the beginning of sentences or paragraphs.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @eekay
    New Auto-Interp
    Negative Logits
     sumpay
    -0.77
     Himo
    -0.68
    quarelle
    -0.68
     revisor
    -0.67
    .。
    -0.67
     Unito
    -0.67
     Allociné
    -0.66
     Ause
    -0.65
    GraphicsUnit
    -0.65
     porcentual
    -0.65
    POSITIVE LOGITS
     shenan
    0.71
     McLaugh
    0.71
     ineffec
    0.70
    lxt
    0.69
     Considerable
    0.69
     philanth
    0.68
     impra
    0.68
     practition
    0.68
     resear
    0.67
     Standardi
    0.67
    Act Density 10.669%

    No Known Activations