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

    Neuronpedia

    INDEX
    Explanations

    mentions of sons at different ages in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "son."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.85
    iculty
    -0.73
    orney
    -0.68
    SOURCE
    -0.65
    irrel
    -0.61
    EFF
    -0.61
    ords
    -0.59
    Journal
    -0.59
    itures
    -0.59
    kefeller
    -0.58
    POSITIVE LOGITS
    hesis
    1.00
    hood
    0.98
     son
    0.90
     Gohan
    0.89
    hetically
    0.87
    nets
    0.84
    ogram
    0.84
    pins
    0.82
    heses
    0.81
    mares
    0.79
    Act Density 0.017%

    No Known Activations