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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ج
    1.27
    ד
    1.26
    ب
    1.17
    ق
    1.13
     that
    1.11
    TA
    1.08
    ش
    1.06
     and
    1.04
    ER
    1.00
     of
    0.97
    POSITIVE LOGITS
    ı
    1.50
    ą
    1.39
    í
    1.38
    ă
    1.33
    in
    1.30
    inė
    1.30
    েন
    1.29
    ̀ng
    1.16
    ího
    1.14
    ü
    1.09
    Act Density 0.000%

    No Known Activations