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

    Neuronpedia

    INDEX
    Explanations

    references to someone or something being alive

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being alive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RECT
    -0.75
    pled
    -0.72
    soDeliveryDate
    -0.69
    ple
    -0.68
    ciples
    -0.66
    wcsstore
    -0.63
    ples
    -0.63
    ij
    -0.63
    ãĥĩ
    -0.62
    liga
    -0.59
    POSITIVE LOGITS
    abouts
    0.95
    lihood
    0.94
     alive
    0.94
    lier
    0.79
     Alive
    0.77
    nces
    0.74
    mares
    0.71
    brates
    0.71
    beat
    0.68
    guards
    0.67
    Act Density 0.025%

    No Known Activations