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

    Neuronpedia

    INDEX
    Explanations

    words related to promotion and advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.66
     
    -0.64
    ara
    -0.62
     y
    -0.60
     two
    -0.60
     AssemblyCulture
    -0.58
    Dieter
    -0.58
     aDecoder
    -0.58
    aha
    -0.57
    녁
    -0.57
    POSITIVE LOGITS
     promotion
    2.08
     promoted
    1.91
     Promotion
    1.88
     promotions
    1.87
     Promote
    1.87
     Promoted
    1.83
     promoting
    1.81
     promote
    1.78
    Promote
    1.77
    promotion
    1.76
    Act Density 0.076%

    No Known Activations