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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their familial relationships.

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

    Family relationships and personal details such as names, dates of birth, and places of origin within a family tree.

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

    first names of people, particularly those that are less common or more distinctive.

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

    Names followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.86
    abestanden
    -0.79
    twimg
    -0.72
    ImageContext
    -0.71
     الرياضيه
    -0.69
    setVerticalGroup
    -0.69
     AssemblyCulture
    -0.68
    AndEndTag
    -0.66
    حياتها
    -0.65
    ScopeManager
    -0.64
    POSITIVE LOGITS
     “
    0.56
    Ashlee
    0.53
     "
    0.52
     electrico
    0.48
     acrílico
    0.46
    adecimal
    0.45
     createSprite
    0.45
    blå
    0.45
     nhiêu
    0.45
     rocz
    0.45
    Act Density 0.067%

    No Known Activations