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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵
    1.58
    س
    1.50
     a
    1.25
    ↵↵
    1.16
    u
    1.15
    b
    1.14
    ↵↵↵
    1.03
    y
    0.98
    ka
    0.95
     to
    0.95
    POSITIVE LOGITS
    of
    1.12
    های
    1.05
    τε
    1.04
    ные
    1.03
    ви
    0.96
    ја
    0.96
    ofu
    0.91
    ље
    0.88
     of
    0.86
    ਤ
    0.85
    Act Density 0.000%

    No Known Activations