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

    Neuronpedia

    INDEX
    Explanations

    instances of family relationships, specifically the word "cousin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships, specifically focusing on cousins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.79
    hner
    -0.75
    inem
    -0.71
    mberg
    -0.69
    gravity
    -0.68
    mble
    -0.67
    ERG
    -0.66
    pter
    -0.65
    manship
    -0.64
    overe
    -0.64
    POSITIVE LOGITS
     nephew
    0.88
     cousins
    0.87
     uncle
    0.86
     cousin
    0.85
     aunt
    0.84
     niece
    0.82
     dolls
    0.74
    hood
    0.73
     relatives
    0.71
    hesis
    0.71
    Act Density 0.021%

    No Known Activations