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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klopp
    -0.17
    æij
    -0.16
    illaume
    -0.15
    gency
    -0.15
    621
    -0.14
     رئ
    -0.14
    ä»Ķ
    -0.14
    emale
    -0.14
    camp
    -0.14
    usu
    -0.14
    POSITIVE LOGITS
    нике
    0.15
    ecal
    0.14
     Strom
    0.14
    StackNavigator
    0.14
    .jar
    0.13
    cerer
    0.13
    -invalid
    0.13
    ANNOT
    0.13
    quarters
    0.13
     Método
    0.13
    Act Density 0.010%

    No Known Activations