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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of relatives and family connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oker
    -0.73
    ane
    -0.72
    OUT
    -0.71
    WM
    -0.71
    argon
    -0.70
    GH
    -0.70
    Effective
    -0.70
    ebook
    -0.70
    oted
    -0.69
    ventory
    -0.69
    POSITIVE LOGITS
     relatives
    1.25
    ilial
    0.87
     cousins
    0.85
     ancestors
    0.85
    folk
    0.82
     arrangements
    0.82
     citiz
    0.82
     aunt
    0.81
     siblings
    0.80
    osponsors
    0.79
    Act Density 0.010%

    No Known Activations