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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ведь
    1.24
     Discrimination
    1.22
     jaws
    1.21
     dara
    1.20
    风格
    1.19
    Aren
    1.18
     jaw
    1.17
    悳
    1.17
     memoirs
    1.17
     Aristotle
    1.16
    POSITIVE LOGITS
    en
    1.20
    in
    1.18
    d
    1.16
    স্ক
    1.15
    dür
    1.13
    வாள
    1.10
    ll
    1.06
    er
    1.05
    s
    1.05
    tors
    1.04
    Act Density 0.000%

    No Known Activations