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

    Neuronpedia

    INDEX
    Explanations

    words related to official obligations or directives

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative mandates or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.88
    stocks
    -0.82
    vae
    -0.76
    ãģį
    -0.72
    hop
    -0.71
    adder
    -0.70
    thel
    -0.69
    enth
    -0.69
    nie
    -0.68
    Ñĭ
    -0.67
    POSITIVE LOGITS
     mandate
    0.87
     mandated
    0.80
     imposed
    0.79
     mandates
    0.79
     requiring
    0.75
     compel
    0.75
     requirement
    0.72
     creep
    0.72
     mand
    0.72
    eers
    0.70
    Act Density 0.016%

    No Known Activations