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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    MBER
    -0.09
     chilled
    -0.07
    blob
    -0.07
     Christina
    -0.07
    mail
    -0.07
    审查
    -0.07
    .ab
    -0.07
    纳
    -0.07
     Bach
    -0.06
    눕
    -0.06
    POSITIVE LOGITS
     sıkıntı
    0.08
    ços
    0.08
    ’é
    0.08
    忑
    0.07
    OMUX
    0.07
    㙍
    0.07
     המציאות
    0.07
    דות
    0.07
     тек
    0.07
    ittings
    0.07
    Act Density 0.002%

    No Known Activations