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

    Neuronpedia

    INDEX
    Explanations

    mentions of transparency and accountability in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.71
    erville
    -0.69
    anova
    -0.67
    awar
    -0.65
    Stars
    -0.64
    enegger
    -0.62
    AMI
    -0.60
    ucky
    -0.60
    ################
    -0.60
    aceous
    -0.60
    POSITIVE LOGITS
    recy
    0.98
    parency
    0.96
     transparency
    0.83
     disclosures
    0.83
     disclosure
    0.82
    rity
    0.80
    ibility
    0.75
     DeVos
    0.75
     Disclosure
    0.74
     transparent
    0.73
    Act Density 0.035%

    No Known Activations