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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    )",
    0.64
    %",
    0.61
    ƒ
    0.59
    क्टूबर
    0.59
    toi
    0.57
    ↵
    0.56
    まして
    0.56
    )',
    0.54
     ẞ
    0.54
    णार्‍या
    0.54
    POSITIVE LOGITS
    ↵↵↵↵
    2.47
    ↵↵↵
    2.41
    ↵↵↵↵↵
    2.32
    ↵↵↵↵↵↵↵
    2.05
    ↵↵↵↵↵↵↵↵↵
    2.03
    ↵↵↵↵↵↵
    2.01
    <eos>
    1.98
    ↵↵↵↵↵↵↵↵
    1.96
    ↵↵
    1.96
    ↵↵↵↵↵↵↵↵↵↵↵
    1.96
    Act Density 2.675%

    No Known Activations