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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal oaths and affirmations

    oai_token-act-pair · gpt-3.5-turbo

    references to oaths and affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stras
    -0.76
    iga
    -0.74
    ========
    -0.67
    Sa
    -0.66
    Mi
    -0.64
    market
    -0.64
    Park
    -0.63
     MEN
    -0.62
    Mini
    -0.62
     NX
    -0.62
    POSITIVE LOGITS
     oath
    1.42
     Oath
    1.07
     sworn
    0.92
    thouse
    0.91
     swearing
    0.90
     vow
    0.88
    breaker
    0.86
    sembly
    0.80
     swore
    0.79
     pledge
    0.78
    Act Density 0.019%

    No Known Activations