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

    Neuronpedia

    INDEX
    Explanations

    names related to a specific person

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    æµ
    -0.65
    æĺ
    -0.61
    ãĤª
    -0.61
     cartel
    -0.59
    ORGE
    -0.59
    ISTER
    -0.59
    ppo
    -0.59
     unnecess
    -0.57
     reckoned
    -0.57
    IME
    -0.57
    POSITIVE LOGITS
    ansas
    1.38
    ozy
    1.27
    entin
    1.07
    itect
    0.98
    eting
    0.95
    anian
    0.95
    iller
    0.94
    patrick
    0.91
    inson
    0.88
    ulic
    0.87
    Act Density 0.109%

    No Known Activations