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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ul
    1.19
    ور
    1.17
    as
    1.07
    im
    0.95
    ad
    0.95
    und
    0.94
    ug
    0.91
    o
    0.90
    amp
    0.90
    id
    0.89
    POSITIVE LOGITS
     to
    1.24
    ۹
    1.24
     and
    1.22
    ה
    1.20
     sired
    1.05
    ン
    1.04
    ツ
    1.04
     $
    1.01
    色の
    0.98
    نی
    0.96
    Act Density 0.000%

    No Known Activations