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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    c
    1.12
    in
    1.07
    t
    1.04
    ad
    1.00
    be
    0.98
    g
    0.96
    p
    0.93
    i
    0.91
    cipher
    0.89
    x
    0.88
    POSITIVE LOGITS
    邺
    0.86
    امج
    0.78
     SUCCESS
    0.76
    िंग
    0.75
    ㄡ
    0.75
     anum
    0.74
    ㄠ
    0.74
     Success
    0.73
    मिथ
    0.73
     संस्थान
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.