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

    Neuronpedia

    INDEX
    Explanations

    questions and statements related to personal experiences and desires

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

    articles and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence-initial function words and first-person conversational markers typical of informal questions and posts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ivelany
    -0.34
     runde
    -0.33
     ujung
    -0.33
     tantôt
    -0.32
     Mancini
    -0.32
     gawas
    -0.32
    <eos>
    -0.32
    vaného
    -0.31
     early
    -0.31
     banda
    -0.31
    POSITIVE LOGITS
    transQ
    0.79
     كومونز
    0.71
    دانشنامهٔ
    0.64
    richTextPanel
    0.62
     surla
    0.60
    XmlAccessType
    0.56
     propOrder
    0.56
    KURZBESCHREIBUNG
    0.54
    homonymie
    0.54
    تقاوى
    0.52
    Act Density 0.099%

    No Known Activations