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

    Neuronpedia

    INDEX
    Explanations

    words related to artificial objects or creations

    oai_token-act-pair · gpt-3.5-turbo

    references to artificiality or artificial constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grab
    -0.79
     Reload
    -0.75
    kb
    -0.74
    review
    -0.74
     Bundy
    -0.71
     Rolling
    -0.71
    rou
    -0.71
    rak
    -0.71
    rc
    -0.69
     Gunn
    -0.67
    POSITIVE LOGITS
     artificial
    3.69
     Artificial
    2.67
     artif
    2.26
     artificially
    2.23
    ificial
    2.20
     synthetic
    1.75
     unnatural
    1.72
     AI
    1.26
     robotic
    1.22
     simulated
    1.12
    Act Density 0.019%

    No Known Activations