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

    Neuronpedia

    INDEX
    Explanations

    references to cake and dessert-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.91
    脚注の使い方
    -0.90
    stateProvider
    -0.89
     plufieurs
    -0.88
     uſed
    -0.88
     avoient
    -0.84
     Theſe
    -0.84
    WebServlet
    -0.83
     myſelf
    -0.83
    Unmarshal
    -0.82
    POSITIVE LOGITS
     card
    0.83
     cake
    0.73
    card
    0.69
     Cake
    0.60
     cards
    0.58
     dia
    0.56
    ana
    0.53
     CAKE
    0.52
    cake
    0.52
    Card
    0.51
    Act Density 0.099%

    No Known Activations