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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence, both in people and artificial entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soda
    -0.83
    soDeliveryDate
    -0.79
    MY
    -0.78
    raine
    -0.76
    rine
    -0.71
     Bundy
    -0.70
    steen
    -0.69
    href
    -0.68
     Gazette
    -0.67
    utz
    -0.67
    POSITIVE LOGITS
     quot
    1.11
    elligent
    0.99
    ively
    0.79
    elligence
    0.79
     Dawkins
    0.74
    smanship
    0.70
     beings
    0.70
    ersion
    0.70
     intelligent
    0.70
    otle
    0.69
    Act Density 0.035%

    No Known Activations