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

    Neuronpedia

    INDEX
    Explanations

    repeated references to the word "same" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.74
    ardı
    -0.70
     découvrez
    -0.68
    ıldız
    -0.67
    déric
    -0.66
     BoxDecoration
    -0.65
    setupUi
    -0.64
     commerciales
    -0.63
    modb
    -0.63
    nani
    -0.63
    POSITIVE LOGITS
     same
    2.87
    same
    2.70
    Same
    2.64
     Same
    2.44
    SAME
    2.36
     SAME
    2.35
     samme
    1.82
     samma
    1.80
     mesma
    1.78
     dezelfde
    1.77
    Act Density 0.067%

    No Known Activations