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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     is
    1.09
    ية
    0.95
    া
    0.89
    )
    0.87
    ৬
    0.85
    )$
    0.84
    。)
    0.78
    )،
    0.77
     leído
    0.74
    ρα
    0.73
    POSITIVE LOGITS
    it
    0.96
    M
    0.88
    W
    0.85
    C
    0.84
    K
    0.84
    ين
    0.80
    P
    0.80
    H
    0.78
    m
    0.76
    S
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.