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

    Neuronpedia

    INDEX
    Explanations

    legal and regulatory terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss legal or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.72
    `
    -0.67
    bernatorial
    -0.66
    andowski
    -0.62
    STAR
    -0.62
    aukee
    -0.61
    iko
    -0.61
    SPA
    -0.60
    ouf
    -0.59
    ãĤ£
    -0.58
    POSITIVE LOGITS
    lining
    1.05
    cutting
    1.03
    pins
    1.02
    lying
    0.97
    neath
    0.96
    graduate
    0.92
    dogs
    0.91
    writing
    0.91
    cuts
    0.90
    lined
    0.90
    Act Density 0.049%

    No Known Activations