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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    m
    1.03
    r
    0.96
    a
    0.92
    sp
    0.89
    d
    0.86
    st
    0.84
    y
    0.82
    the
    0.82
    b
    0.80
    en
    0.80
    POSITIVE LOGITS
     inductively
    0.84
     وعند
    0.82
     acidified
    0.81
     چڑھ
    0.80
     ܀
    0.80
     lentils
    0.79
     obtenus
    0.79
    퐶
    0.79
    ऑक्साइड
    0.79
    めます
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.