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

    Neuronpedia

    INDEX
    Explanations

    mentions of someone being alive

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RECT
    -0.70
    soDeliveryDate
    -0.64
    cipl
    -0.63
     Aerospace
    -0.62
     Telescope
    -0.61
    ãĥĩ
    -0.60
     Responsibility
    -0.59
     responsibility
    -0.58
    Prin
    -0.57
    agall
    -0.57
    POSITIVE LOGITS
    lihood
    1.03
    abouts
    0.80
     alive
    0.80
    terday
    0.76
    nces
    0.74
    spin
    0.74
    beat
    0.73
    weight
    0.73
    mares
    0.71
    arbon
    0.70
    Act Density 0.073%

    No Known Activations