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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and judicial situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pyramid
    -0.57
     Amon
    -0.57
     Mash
    -0.57
     trainer
    -0.56
     disguised
    -0.56
     mathemat
    -0.56
     nicknamed
    -0.56
     wors
    -0.55
     flourishing
    -0.55
     mounted
    -0.55
    POSITIVE LOGITS
    onto
    0.90
    ï¸ı
    0.90
    their
    0.89
    them
    0.89
    orders
    0.82
    him
    0.81
    selves
    0.81
    rough
    0.77
    his
    0.76
    your
    0.76
    Act Density 0.215%

    No Known Activations