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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    0.50
     ([
    0.47
     ((
    0.44
     капита
    0.42
    ierd
    0.41
    傥
    0.41
    kses
    0.39
    ([
    0.39
    midrule
    0.38
    ks
    0.38
    POSITIVE LOGITS
     caratter
    0.54
     ਹੋ
    0.50
     lavori
    0.49
     Siena
    0.47
     lavorare
    0.47
    कार्य
    0.45
     початку
    0.44
     diseñ
    0.44
     Belle
    0.44
     riserv
    0.44
    Act Density 0.005%

    No Known Activations