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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    1.23
    am
    1.20
     aujourd
    1.20
    atik
    1.20
    ag
    1.16
     consommateurs
    1.16
    ни
    1.14
    то
    1.13
    aties
    1.11
     cadeaux
    1.10
    POSITIVE LOGITS
    ף
    1.38
    에는
    1.30
    Während
    1.30
    การ
    1.29
     TNF
    1.18
    のア
    1.17
     AMG
    1.17
    되는
    1.16
    ное
    1.14
    에서의
    1.10
    Act Density 0.056%

    No Known Activations