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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    on
    1.59
    О
    1.30
    나
    1.28
    of
    1.26
    Ф
    1.17
    It
    1.14
    П
    1.14
    一个
    1.13
    问题
    1.10
    上
    1.07
    POSITIVE LOGITS
    i
    1.13
     robuste
    0.99
    ної
    0.96
    t
    0.96
     bicovariant
    0.94
     geotechnical
    0.90
     volat
    0.89
     seconde
    0.89
    arbeiter
    0.88
     grosso
    0.88
    Act Density 0.000%

    No Known Activations