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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ul
    0.65
    ب
    0.58
    िक
    0.55
    n
    0.54
    s
    0.53
    يا
    0.51
    其他
    0.50
    های
    0.49
    ą
    0.49
    م
    0.48
    POSITIVE LOGITS
    ۰
    0.81
    ↵
    0.64
    ।’
    0.59
     can
    0.58
    ।
    0.58
    ۵
    0.57
     I
    0.55
    ۹
    0.54
    ,’
    0.53
    ।”
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.