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

    Neuronpedia

    INDEX
    Explanations

    mention of being alive or surviving

    oai_token-act-pair · gpt-3.5-turbo

    mentions of being alive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RECT
    -0.73
     Aerospace
    -0.67
    agall
    -0.64
    soDeliveryDate
    -0.63
    addy
    -0.62
    ãĥĩ
    -0.62
    cipl
    -0.61
    ple
    -0.59
    ij
    -0.59
    pled
    -0.59
    POSITIVE LOGITS
    lihood
    1.09
    abouts
    0.84
    nces
    0.81
     alive
    0.80
    spin
    0.72
    lier
    0.71
    mares
    0.71
    weight
    0.70
    beat
    0.70
    eem
    0.68
    Act Density 0.033%

    No Known Activations