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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to promoting or supporting initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.81
     y
    -0.69
    녁
    -0.62
     qui
    -0.62
     most
    -0.61
    Dieter
    -0.61
    ara
    -0.60
    Kita
    -0.59
    晴
    -0.59
     two
    -0.58
    POSITIVE LOGITS
     myſelf
    1.25
     Promoted
    1.24
     Promote
    1.20
     themſelves
    1.16
     Monfieur
    1.16
     Promotes
    1.16
     promotion
    1.15
     purpoſe
    1.14
    Promote
    1.12
     pleaſure
    1.11
    Act Density 0.087%

    No Known Activations