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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    1.01
     are
    0.97
     be
    0.89
     is
    0.82
    ется
    0.82
     an
    0.73
     it
    0.70
    {
    0.68
     as
    0.68
    ۔
    0.67
    POSITIVE LOGITS
    an
    1.25
    u
    1.16
    in
    1.09
    a
    1.09
    z
    1.05
    p
    1.02
    on
    0.96
    et
    0.96
    x
    0.96
    k
    0.96
    Act Density 0.000%

    No Known Activations