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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (
    1.93
    ing
    1.79
    ra
    1.40
    as
    1.32
    er
    1.25
    ere
    1.20
    the
    1.20
    z
    1.20
    le
    1.17
    el
    1.17
    POSITIVE LOGITS
    。
    1.13
    知道
    1.05
    د
    1.05
    的价格
    1.02
    。「
    1.01
    на
    0.96
    이나
    0.95
     voork
    0.95
     ។
    0.92
    也就是说
    0.92
    Act Density 0.000%

    No Known Activations