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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ar
    1.41
    l
    1.21
    de
    1.13
    rijke
    1.11
    itism
    1.09
    rances
    1.05
    stricken
    1.03
    ier
    1.03
    بری
    1.02
    arag
    1.02
    POSITIVE LOGITS
     sienta
    1.32
     ہُ
    1.27
     sient
    1.26
     versuchen
    1.26
     llega
    1.24
     theorists
    1.23
     vont
    1.23
     kebanyakan
    1.23
     نشوف
    1.22
     Tagen
    1.22
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.