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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    1.59
    （
    1.49
     （
    1.24
    (
    1.05
     ((
    0.98
    ((
    0.97
    。（
    0.94
     (`
    0.87
    (){
    0.85
    ：（
    0.85
    POSITIVE LOGITS
    )
    4.57
    ),
    4.42
    ).
    4.29
    )،
    4.27
    )。
    4.10
    !)
    4.06
    ):
    4.04
    ?)
    3.93
    );
    3.90
    )।
    3.90
    Act Density 3.425%

    No Known Activations