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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and parental roles

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

    Tokens preceding people's first names

    np_acts-logits-general · gemini-2.0-flash

    people and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.43
    udy
    -0.43
     betweenstory
    -0.42
    ubit
    -0.42
    AH
    -0.41
     Cons
    -0.40
    الحياه
    -0.40
    rica
    -0.40
    lay
    -0.40
    новништво
    -0.40
    POSITIVE LOGITS
    enderror
    0.50
     parenting
    0.47
    GIVEREF
    0.43
    atchewan
    0.43
    UpInside
    0.42
    Архівовано
    0.41
    BufferException
    0.41
     Normdatei
    0.41
    教
    0.41
    率
    0.41
    Act Density 0.418%

    No Known Activations