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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal legal proceedings and documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.98
     pleaſure
    -0.98
     greateſt
    -0.94
    IntoConstraints
    -0.93
     ſeveral
    -0.91
     Majefty
    -0.91
     Efq
    -0.90
     myſelf
    -0.89
     purpoſe
    -0.88
     Reſ
    -0.87
    POSITIVE LOGITS
     of
    0.86
    /
    0.59
    <eos>
    0.58
     for
    0.57
    ']}
    0.57
     in
    0.56
     list
    0.54
     to
    0.54
     program
    0.53
     ab
    0.51
    Act Density 1.234%

    No Known Activations