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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ечно
    -0.07
     Exactly
    -0.07
    失去了
    -0.07
     Qué
    -0.07
    ivement
    -0.06
    Color
    -0.06
     irrelevant
    -0.06
    Aceptar
    -0.06
     disconnect
    -0.06
     perché
    -0.06
    POSITIVE LOGITS
    grid
    0.06
    {-#
    0.06
    연구
    0.06
    אפליק
    0.06
    设想
    0.06
    layer
    0.06
     jä
    0.06
    }/>↵
    0.06
    layers
    0.06
     studios
    0.06
    Act Density 0.054%

    No Known Activations