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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     matched
    0.47
    '
    0.45
    ’
    0.45
     shouted
    0.44
    事業
    0.44
     grouped
    0.43
     shuffled
    0.41
    ి
    0.41
     piloted
    0.41
     hurled
    0.41
    POSITIVE LOGITS
     Erschein
    0.50
     Mira
    0.46
     Новый
    0.45
     Allison
    0.45
     除了
    0.45
    Digite
    0.45
    ↵↵↵
    0.45
     新
    0.44
     Wszyst
    0.44
     Seg
    0.44
    Act Density 0.003%

    No Known Activations