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

    Neuronpedia

    INDEX
    Explanations

    examples of diverse groups or communities

    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
    rol
    -0.72
    WARD
    -0.70
    keeper
    -0.69
    WAR
    -0.67
    cel
    -0.67
    çĶ°
    -0.66
    FORE
    -0.65
    closed
    -0.64
    OD
    -0.64
    rollers
    -0.64
    POSITIVE LOGITS
    mble
    0.96
    ively
    0.92
     perspectives
    0.92
     facets
    0.91
    ortment
    0.90
     genders
    0.89
    iating
    0.89
     assemb
    0.89
    iated
    0.86
     avenues
    0.85
    Act Density 0.039%

    No Known Activations