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

    Neuronpedia

    INDEX
    Explanations

    references to fairness in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    copg
    -0.65
    endpush
    -0.58
     ModelExpression
    -0.52
    AutoresizingMask
    -0.51
    ServletException
    -0.51
    ually
    -0.49
    roduction
    -0.48
    pann
    -0.47
    めでとう
    -0.47
    JoinColumn
    -0.46
    POSITIVE LOGITS
    ytale
    1.00
    yt
    0.82
    grounds
    0.77
    weather
    0.77
    ground
    0.75
    trade
    0.72
    erweise
    0.70
     trade
    0.67
     Dink
    0.66
     skinned
    0.65
    Act Density 0.217%

    No Known Activations