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

    Neuronpedia

    INDEX
    Explanations

    mentions of family relationships, specifically the word 'cousin'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships, specifically involving cousins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.84
    hner
    -0.83
    Ö¼
    -0.74
    mberg
    -0.74
    overe
    -0.73
    inen
    -0.72
    yk
    -0.71
    enium
    -0.70
     largeDownload
    -0.69
    yss
    -0.69
    POSITIVE LOGITS
     cousins
    0.98
     cousin
    0.97
     uncle
    0.92
     aunt
    0.91
     nephew
    0.88
     niece
    0.86
    hesis
    0.82
     incest
    0.76
    hood
    0.76
    hetical
    0.70
    Act Density 0.011%

    No Known Activations