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

    Neuronpedia

    INDEX
    Explanations

    phrases that include identifying information about people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.56
     Вікі
    -0.55
    раздо
    -0.54
    reciate
    -0.54
     Ouvrez
    -0.53
    人民共和国
    -0.52
    enderror
    -0.51
     disponibilités
    -0.48
    manera
    -0.48
    JspWriter
    -0.48
    POSITIVE LOGITS
    autogui
    0.68
    });*/
    0.67
     originally
    0.65
    )*/
    0.64
    }*/
    0.64
    GetMapping
    0.64
    previously
    0.62
    ''');
    0.61
    BeginContext
    0.61
    });
    0.60
    Act Density 0.218%

    No Known Activations