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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     both
    2.00
    省略
    1.77
     Leaving
    1.74
     adjournment
    1.73
     leaving
    1.71
    dated
    1.69
     /.
    1.68
     occasionally
    1.67
     itself
    1.67
     [&
    1.66
    POSITIVE LOGITS
    ٧
    1.98
    ٦
    1.85
    тем
    1.82
    ٥
    1.80
     верх
    1.76
    ٨
    1.74
     цветов
    1.71
     арт
    1.69
     сути
    1.68
     рост
    1.68
    Act Density 0.690%

    No Known Activations