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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     the
    1.46
    1
    1.42
    .
    1.38
     a
    1.30
    2
    1.25
    the
    1.22
    4
    1.16
     а
    1.15
     thei
    1.13
    ,
    1.12
    POSITIVE LOGITS
     is
    1.08
    ૦
    0.96
     are
    0.94
     I
    0.93
     hanno
    0.92
     can
    0.91
     จ
    0.91
     ช
    0.89
     Cơ
    0.89
     has
    0.88
    Act Density 0.786%

    No Known Activations