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

    Neuronpedia

    INDEX
    Explanations

    terms related to diversity and inclusivity

    oai_token-act-pair · gpt-3.5-turbo

    references to diversity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENA
    -0.93
    amina
    -0.83
    FIN
    -0.77
    DA
    -0.76
    ving
    -0.73
    INK
    -0.72
    ש
    -0.72
    mentioned
    -0.71
    MER
    -0.70
    CHA
    -0.69
    POSITIVE LOGITS
     diversity
    1.01
     Diversity
    0.98
    yip
    0.82
    ensical
    0.81
    iveness
    0.80
    icultural
    0.78
    ĸļ
    0.74
    atility
    0.73
    halla
    0.70
    ortment
    0.69
    Act Density 0.013%

    No Known Activations