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

    Neuronpedia

    INDEX
    Explanations

    references related to family members, particularly sons

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "son."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.80
    iculty
    -0.77
    orney
    -0.65
    kefeller
    -0.64
     freight
    -0.62
    Population
    -0.61
    PORT
    -0.60
    SOURCE
    -0.60
    [_
    -0.59
    Credit
    -0.59
    POSITIVE LOGITS
    hood
    0.96
    hesis
    0.95
     Gohan
    0.94
    pins
    0.89
     son
    0.88
    heses
    0.88
    ogram
    0.86
    friend
    0.84
    mares
    0.82
    hetically
    0.80
    Act Density 0.020%

    No Known Activations