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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to smoking bans and their effects on health outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demos
    -0.74
     Tycoon
    -0.72
     pulp
    -0.71
     presentations
    -0.70
     Trance
    -0.70
     Teach
    -0.69
     Pod
    -0.69
     RTX
    -0.68
     liter
    -0.68
     IMAGES
    -0.67
    POSITIVE LOGITS
     imposed
    1.38
     enforced
    1.32
     preventing
    1.09
     abolished
    1.04
     restricting
    1.04
     prohibiting
    1.04
     enforce
    1.03
    escal
    1.02
     deterrent
    1.02
     draconian
    1.02
    Act Density 0.577%

    No Known Activations