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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ▐
    -0.07
     Casa
    -0.07
     العالمية
    -0.07
     Fake
    -0.07
     Te
    -0.07
    .te
    -0.06
    aq
    -0.06
    -off
    -0.06
     cultivated
    -0.06
    brief
    -0.06
    POSITIVE LOGITS
     Drain
    0.07
    會員
    0.07
    Routes
    0.07
     réal
    0.07
    /models
    0.07
    erusform
    0.07
    /entities
    0.07
    刘备
    0.07
    撂
    0.07
    往往会
    0.07
    Act Density 0.027%

    No Known Activations