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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    positivo
    0.86
     novelist
    0.82
     novelists
    0.81
     литератур
    0.79
     supreme
    0.79
    ෘ
    0.79
    ខ្
    0.78
     creativa
    0.78
     augmented
    0.77
    enh
    0.77
    POSITIVE LOGITS
    対象
    1.54
     excluded
    1.41
     대상
    1.30
    纳入
    1.29
     대상으로
    1.28
    Excluded
    1.27
    exclude
    1.26
     제외
    1.25
     seznam
    1.24
    遍历
    1.24
    Act Density 0.440%

    No Known Activations