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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     they
    0.46
    they
    0.41
    Placeholder
    0.41
     می‌تواند
    0.40
    no
    0.39
    ebilir
    0.39
    current
    0.39
    Plan
    0.39
    atering
    0.38
    >`
    0.38
    POSITIVE LOGITS
     법
    0.51
    互相
    0.50
     得
    0.49
    法
    0.48
    得
    0.48
    法的
    0.46
    互
    0.44
    법
    0.44
     ought
    0.43
     law
    0.42
    Act Density 0.000%

    No Known Activations