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

    Neuronpedia

    INDEX
    Explanations

    legal terms and phrases, particularly those related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to common laws and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eki
    -0.87
    ĸļ
    -0.79
    omo
    -0.76
    bye
    -0.71
    olulu
    -0.69
    psey
    -0.69
     hurd
    -0.69
    wagen
    -0.68
     Mehran
    -0.68
    kok
    -0.66
    POSITIVE LOGITS
    ensical
    1.08
    rences
    1.02
     Uncommon
    0.76
    runtime
    0.75
    ãĤ¶
    0.73
    rities
    0.71
    Across
    0.70
     amongst
    0.69
    pmwiki
    0.69
    \">
    0.65
    Act Density 0.184%

    No Known Activations