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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Der
    -0.07
    contexts
    -0.07
    _plots
    -0.07
     markers
    -0.07
     רבים
    -0.07
     Гр
    -0.07
     Election
    -0.07
     Sim
    -0.06
     autumn
    -0.06
    Rub
    -0.06
    POSITIVE LOGITS
    特意
    0.07
     commande
    0.07
     accuse
    0.07
     pronounced
    0.07
    🤣
    0.07
    /T
    0.06
     pleasantly
    0.06
    .getPrice
    0.06
    GHz
    0.06
     adorable
    0.06
    Act Density 0.004%

    No Known Activations