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

    Neuronpedia

    INDEX
    Explanations

    specific names, terms, or references related to talent shows, events, and artistic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elbe
    -0.84
    Referências
    -0.74
     rita
    -0.74
     Fang
    -0.72
    Clr
    -0.71
     espri
    -0.70
     Dolores
    -0.70
    érienne
    -0.70
    Fang
    -0.70
    biter
    -0.70
    POSITIVE LOGITS
    )");
    0.96
    )");
    0.88
    Rav
    0.88
    >>();
    0.86
     Maddox
    0.81
     Gav
    0.81
     Avic
    0.79
    :])
    0.79
     Antropo
    0.78
     }}"></
    0.77
    Act Density 9.762%

    No Known Activations