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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pour
    -0.08
    @g
    -0.07
    苜
    -0.07
    晁
    -0.07
     MOTOR
    -0.07
    fram
    -0.06
    皈
    -0.06
    inia
    -0.06
     g
    -0.06
    elor
    -0.06
    POSITIVE LOGITS
     Москвы
    0.07
    )];
↵
    0.07
    -mf
    0.07
     "]
    0.07
    innitus
    0.07
    vised
    0.07
    潜能
    0.07
    的合作
    0.06
    됬
    0.06
    ʸ
    0.06
    Act Density 0.001%

    No Known Activations