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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to sections or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elfth
    -0.76
    $_['
    -0.60
    onAttach
    -0.54
    ⓧ
    -0.54
    ########.
    -0.51
    PhysRev
    -0.50
    日閲覧
    -0.48
     للمعارف
    -0.48
    usepackage
    -0.48
    Spoljašnje
    -0.48
    POSITIVE LOGITS
    "]);
    0.83
    "])
    0.83
    ==",
    0.80
    "]];
    0.79
    "],
    0.79
    "):
    0.79
    "।
    0.79
    ")));
    0.79
    ":
    0.78
    '},
    0.74
    Act Density 0.921%

    No Known Activations