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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beginners and learning

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aughters
    -1.01
    apa
    -0.83
     Parenthood
    -0.81
    oret
    -0.79
     assass
    -0.79
    iola
    -0.76
    har
    -0.75
    Ĥİ
    -0.74
     Mehran
    -0.74
     indefinite
    -0.74
    POSITIVE LOGITS
    clair
    0.94
     minded
    0.94
     browsing
    0.93
     acquainted
    0.92
    pora
    0.89
    é¾įåĸļ士
    0.87
     alike
    0.87
    sbm
    0.86
    theless
    0.86
    nings
    0.86
    Act Density 2.733%

    No Known Activations