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

    Neuronpedia

    INDEX
    Explanations

    mentions of artificial intelligence or artificial additives

    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
    wick
    -0.81
    etts
    -0.79
    ochet
    -0.78
    night
    -0.77
    src
    -0.77
    ebook
    -0.77
    worthy
    -0.76
    roud
    -0.75
    gerald
    -0.73
    rike
    -0.73
    POSITIVE LOGITS
     artificial
    0.92
     artif
    0.81
     intelligence
    0.80
     turf
    0.80
    ificial
    0.77
     fertil
    0.76
    ized
    0.74
    intelligence
    0.73
     wom
    0.73
     reef
    0.73
    Act Density 0.008%

    No Known Activations