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

    Neuronpedia

    INDEX
    Explanations

    words related to laws and regulatory processes

    oai_token-act-pair · gpt-3.5-turbo

    references to regulations or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.88
    ience
    -0.84
    strap
    -0.76
    joy
    -0.76
     Neh
    -0.75
    lihood
    -0.75
    ãĥİ
    -0.74
    ãĥ¤
    -0.71
    ocent
    -0.71
    ãĥĦ
    -0.68
    POSITIVE LOGITS
     promulg
    1.11
     governing
    1.11
     imposed
    1.09
     regulating
    0.94
     permitting
    0.93
     enforcement
    0.91
     enforced
    0.91
     filings
    0.89
     levied
    0.88
     prescribed
    0.86
    Act Density 0.024%

    No Known Activations