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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    T
    0.56
     the
    0.55
    W
    0.53
    com
    0.52
    A
    0.50
    C
    0.50
    P
    0.50
    ac
    0.49
    S
    0.49
    1
    0.48
    POSITIVE LOGITS
    <unused764>
    1.06
    );//
    1.04
    );
    1.03
    𐰇
    1.03
    ;//
    1.02
    1.00
    <unused2060>
    0.98
     auxqu
    0.98
    ৤
    0.98
     messageShow
    0.97
    Act Density 2.705%

    No Known Activations