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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     s
    0.52
    s
    0.49
     (
    0.46
     damp
    0.46
    ,
    0.45
     ak
    0.44
     mis
    0.44
     w
    0.43
     tam
    0.42
     fl
    0.42
    POSITIVE LOGITS
    <unused637>
    0.85
    <unused1769>
    0.84
     Кстати
    0.81
    ግሎ
    0.80
    <unused1763>
    0.79
    <unused440>
    0.79
    Além
    0.78
    <unused767>
    0.78
    <unused1851>
    0.77
    <unused1663>
    0.77
    Act Density 2.054%

    No Known Activations