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

    Neuronpedia

    INDEX
    Explanations

    terms related to different industries or societal issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various social, ethical, and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.73
    ortium
    -0.58
    arnaev
    -0.56
    emale
    -0.55
     Ladies
    -0.54
    lihood
    -0.53
    Ĭ±
    -0.53
     Jub
    -0.53
     Prix
    -0.52
     Dob
    -0.52
    POSITIVE LOGITS
    bugs
    0.65
     barriers
    0.61
     discrimination
    0.61
     therapy
    0.60
     sickness
    0.58
     avoidance
    0.58
     aggregation
    0.57
     regulators
    0.56
     accidents
    0.56
     pollution
    0.55
    Act Density 0.606%

    No Known Activations