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

    Neuronpedia

    INDEX
    Explanations

    words related to rules, laws, and guidelines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.97
    ience
    -0.86
    joy
    -0.80
    strap
    -0.75
    ocent
    -0.75
     Neh
    -0.69
    vic
    -0.69
    stocks
    -0.68
    lihood
    -0.68
    ãĥİ
    -0.68
    POSITIVE LOGITS
     promulg
    1.12
     governing
    1.10
     imposed
    1.03
     regulating
    0.92
     permitting
    0.92
     enforcement
    0.87
     levied
    0.85
     enforced
    0.84
     prescribed
    0.84
     exempt
    0.84
    Act Density 0.024%

    No Known Activations