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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     تركيا
    -0.07
    申し
    -0.07
    ᕕ
    -0.07
     będę
    -0.07
     Bren
    -0.07
    Miss
    -0.07
    แชม
    -0.07
    씬
    -0.07
    中国政府
    -0.06
     cerv
    -0.06
    POSITIVE LOGITS
    >|
    0.08
    }|
    0.07
    ="[
    0.07
    (`/
    0.07
     |-
    0.07
    يار
    0.07
     insults
    0.07
    -input
    0.07
    Helpers
    0.06
    퉤
    0.06
    Act Density 0.011%

    No Known Activations