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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing the process of making decisions or causing actions to happen

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Recife
    -0.59
     Giugno
    -0.59
     Pernambuco
    -0.59
     gmbh
    -0.58
     Lombar
    -0.57
     stoff
    -0.55
     Verk
    -0.55
     Curitiba
    -0.55
     Luglio
    -0.54
     biograf
    -0.53
    POSITIVE LOGITS
    Makes
    0.94
     Makes
    0.90
     make
    0.90
    make
    0.88
    Make
    0.88
    makes
    0.88
     MAKE
    0.88
     MAKES
    0.86
     makes
    0.85
     Make
    0.83
    Act Density 0.160%

    No Known Activations