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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ский
    1.20
     piety
    1.10
    িয়া
    1.08
    吺
    1.05
     wills
    1.05
     assassins
    1.04
     забра
    1.04
     renown
    1.03
     DCs
    1.03
     ills
    1.01
    POSITIVE LOGITS
    t
    1.44
    T
    1.43
    as
    1.36
    am
    1.27
     T
    1.20
    ut
    1.20
    ar
    1.19
    ᴛ
    1.19
    y
    1.19
    x
    1.14
    Act Density 0.000%

    No Known Activations