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

    Neuronpedia

    INDEX
    Explanations

    actions related to promotion and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.73
     two
    -0.69
     most
    -0.67
    Dieter
    -0.63
     y
    -0.62
    mtable
    -0.62
    ara
    -0.61
     FE
    -0.61
     not
    -0.60
    晴
    -0.60
    POSITIVE LOGITS
     promotion
    1.59
     Promoted
    1.58
     Promote
    1.54
     promoted
    1.50
     promotions
    1.48
     Promotion
    1.47
     promoting
    1.45
    Promote
    1.45
    promoted
    1.41
     promotes
    1.40
    Act Density 0.093%

    No Known Activations