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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    토
    0.74
    ס
    0.72
    he
    0.71
    לי
    0.70
    ru
    0.68
    YOU
    0.68
    hg
    0.68
    คุณ
    0.68
    年生
    0.65
    Y
    0.65
    POSITIVE LOGITS
     agradecer
    0.85
    ergewöhn
    0.85
     únicamente
    0.84
     descubrir
    0.84
    ┈
    0.83
    ンダー
    0.83
     útiles
    0.82
     agrade
    0.82
     πιο
    0.82
     чуть
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.