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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abel
    -0.08
     fruitful
    -0.08
     fourth
    -0.08
    ======
    -0.08
     On
    -0.08
    amanho
    -0.07
    ἤ
    -0.07
     el
    -0.07
    席
    -0.07
    어요
    -0.07
    POSITIVE LOGITS
     Russian
    0.08
    普京
    0.08
     villagers
    0.08
     russ
    0.07
     encoded
    0.07
    俄
    0.07
     Russians
    0.07
    俄军
    0.07
    水中
    0.07
    为代表的
    0.07
    Act Density 0.023%

    No Known Activations