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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members or familial relationships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "family."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    generated
    -0.75
    Gamer
    -0.68
    Downloadha
    -0.66
    NetMessage
    -0.66
    hematically
    -0.62
    posted
    -0.62
    Result
    -0.61
    Kick
    -0.61
    wei
    -0.61
     WITHOUT
    -0.61
    POSITIVE LOGITS
     family
    3.50
    family
    2.78
    Family
    2.76
     Family
    2.56
     families
    2.41
     relatives
    2.03
     familial
    1.85
     Families
    1.79
     household
    1.77
     siblings
    1.72
    Act Density 0.034%

    No Known Activations