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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start or end of events or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewis
    -0.16
    pedia
    -0.16
    plib
    -0.15
    çĥĪ
    -0.15
    ês
    -0.15
    ouv
    -0.15
    िà¤
    -0.15
    ä»Ĭ
    -0.14
     Rub
    -0.14
    ESS
    -0.14
    POSITIVE LOGITS
     stages
    0.23
    game
    0.18
     credits
    0.18
    credits
    0.18
    -middle
    0.18
    earing
    0.16
     RuntimeObject
    0.16
    Credits
    0.15
     Credits
    0.15
    /end
    0.15
    Act Density 0.037%

    No Known Activations