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

    Neuronpedia

    INDEX
    Explanations

    words related to legal proceedings and oaths

    oai_token-act-pair · gpt-3.5-turbo

    references to oaths or pledges of truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stras
    -0.72
    ========
    -0.71
    iga
    -0.69
    Sa
    -0.68
    aple
    -0.68
    nesota
    -0.66
    ppa
    -0.65
    Mini
    -0.65
     SEN
    -0.65
     Cater
    -0.64
    POSITIVE LOGITS
     oath
    1.34
     Oath
    1.11
     sworn
    1.01
    ylum
    0.89
    breaker
    0.87
     vow
    0.87
     swearing
    0.84
    naire
    0.82
    thouse
    0.82
    bringer
    0.79
    Act Density 0.008%

    No Known Activations