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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that indicate a conclusion, summary, or important point being made in the text.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    significant events and changes in narratives

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

    Text after punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    response measure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geï
    -0.34
     experimentally
    -0.33
    ‌اند
    -0.32
    ี่ยว
    -0.32
     Rechte
    -0.31
    komp
    -0.31
    ITÉ
    -0.31
    HttpGet
    -0.31
    startIndex
    -0.31
    forsk
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    0.76
     kasarigan
    0.73
     المعيارى
    0.71
     oprot
    0.62
    jspb
    0.60
    GEBURTSDATUM
    0.59
     ComVisible
    0.58
    RectangleBorder
    0.57
     Autorizaciones
    0.57
    =$?
    0.55
    Act Density 0.512%

    No Known Activations