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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and regulatory actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bard
    -0.78
    boy
    -0.68
    iano
    -0.66
    kaya
    -0.64
    been
    -0.64
    tex
    -0.63
    arse
    -0.63
    bow
    -0.63
    halla
    -0.63
    ko
    -0.62
    POSITIVE LOGITS
     us
    1.16
     users
    0.98
     him
    0.96
     them
    0.95
     viewers
    0.91
     recipients
    0.90
     me
    0.88
     individuals
    0.88
     people
    0.86
     visitors
    0.86
    Act Density 1.780%

    No Known Activations