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

    Neuronpedia

    INDEX
    Explanations

    references to laws and legal principles, particularly in the context of governmental or constitutional matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enforcing
    -0.15
     Slate
    -0.14
     Lodge
    -0.14
     Sist
    -0.14
    ced
    -0.14
     iv
    -0.13
     rejection
    -0.13
    ãģ¼
    -0.13
     Typed
    -0.13
    ayet
    -0.13
    POSITIVE LOGITS
    allows
    0.18
    è§Ħå®ļ
    0.16
    jem
    0.16
     requires
    0.16
    ì§ĢëıĦ
    0.16
    åħģ
    0.15
    езда
    0.15
    require
    0.15
     says
    0.15
     explicitly
    0.15
    Act Density 0.204%

    No Known Activations