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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ين
    1.34
     H
    1.05
    M
    1.03
     J
    1.01
    K
    0.98
    T
    0.98
     B
    0.96
    ﺭ
    0.96
     M
    0.95
     S
    0.93
    POSITIVE LOGITS
    )$,
    1.04
    this
    1.03
    zelfde
    0.97
    that
    0.96
    the
    0.94
    cdot
    0.93
    nelles
    0.93
    arı
    0.89
    ences
    0.88
    ,",
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.