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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to laws, regulations, or legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Under" followed by various numerical values, indicating regulations or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.77
    bernatorial
    -0.71
    76561
    -0.68
     Scand
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
     distur
    -0.60
     professionally
    -0.58
     hereafter
    -0.58
     scratch
    -0.58
    ãĥ£
    -0.57
    POSITIVE LOGITS
    neath
    1.28
    lying
    1.12
    graduate
    1.02
    Ļ½
    1.00
    stant
    0.96
    mining
    0.95
    flows
    0.93
    grad
    0.92
    cover
    0.91
    lining
    0.91
    Act Density 0.028%

    No Known Activations