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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships, particularly sons

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, particularly the term "son."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.75
    jriwal
    -0.66
    urg
    -0.65
     deterior
    -0.65
    eers
    -0.64
    ommod
    -0.63
    FOR
    -0.63
    ontent
    -0.63
    asonable
    -0.60
     demon
    -0.59
    POSITIVE LOGITS
    nets
    0.90
    heses
    0.88
    hesis
    0.88
    hetically
    0.82
    hood
    0.69
    wife
    0.67
    pins
    0.66
    eatures
    0.65
    hetical
    0.65
     Kath
    0.62
    Act Density 0.089%

    No Known Activations