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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing confidence or assurance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.79
    pmwiki
    -0.79
    kay
    -0.71
    mes
    -0.69
    perse
    -0.67
    nice
    -0.67
    artifacts
    -0.66
    theme
    -0.66
    çĦ
    -0.65
    anie
    -0.65
    POSITIVE LOGITS
    ially
    1.11
    worthiness
    1.07
     intervals
    0.89
    lessly
    0.83
     assurance
    0.81
    iated
    0.79
    worthy
    0.72
    ively
    0.71
     confidence
    0.70
     assurances
    0.69
    Act Density 0.107%

    No Known Activations