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

    Neuronpedia

    INDEX
    Explanations

    references to artificial materials or intelligence

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.76
    ï¸ı
    -0.75
    src
    -0.71
     Blessed
    -0.71
     Transcript
    -0.70
    ires
    -0.69
    ippers
    -0.68
    -0.67
    Brother
    -0.67
    EF
    -0.67
    POSITIVE LOGITS
     artificial
    1.28
     artif
    1.25
    ificial
    1.17
     Artificial
    1.09
     artificially
    0.89
     automation
    0.81
     ventilation
    0.77
     satell
    0.74
    MpServer
    0.74
     immersion
    0.73
    Act Density 0.006%

    No Known Activations