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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "artificial intelligence"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gings
    -0.16
    Č↵
    -0.15
    sector
    -0.15
    peaker
    -0.15
    436
    -0.14
    аÑģÑĤи
    -0.14
    atical
    -0.14
    731
    -0.14
    _deinit
    -0.14
     buurt
    -0.14
    POSITIVE LOGITS
     intelligence
    0.49
     Intelligence
    0.44
    intelligence
    0.38
     intelig
    0.33
    elligence
    0.29
     intelligent
    0.29
    ificial
    0.28
     Intelligent
    0.27
     intel
    0.26
     intellig
    0.26
    Act Density 0.009%

    No Known Activations