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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cousin" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships, specifically focusing on cousins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.93
    hner
    -0.87
    ilipp
    -0.79
    overe
    -0.79
    yss
    -0.79
     largeDownload
    -0.77
    arching
    -0.76
    mberg
    -0.74
    Ö¼
    -0.73
    phis
    -0.72
    POSITIVE LOGITS
     cousin
    1.02
     cousins
    0.97
     nephew
    0.92
     niece
    0.87
     aunt
    0.86
     uncle
    0.84
    hesis
    0.75
     tutor
    0.71
    hood
    0.70
     sister
    0.70
    Act Density 0.006%

    No Known Activations