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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms related to safety standards and risk assessment in robotics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.70
    stein
    -0.70
    liest
    -0.68
    ners
    -0.66
     joke
    -0.66
     sidel
    -0.65
     symp
    -0.65
     jokes
    -0.62
     Cats
    -0.61
    aughs
    -0.61
    POSITIVE LOGITS
    ullivan
    1.00
    weet
    1.00
    ierra
    0.93
    BUR
    0.93
    ocial
    0.92
    WER
    0.91
    omething
    0.90
    EC
    0.89
    arnaev
    0.88
    MC
    0.87
    Act Density 0.014%

    No Known Activations