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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    돕
    -0.08
    OVER
    -0.07
    ומנים
    -0.07
     الأمريك
    -0.07
    ᠰ
    -0.07
    Industry
    -0.07
    ploy
    -0.07
    Aug
    -0.07
    통신
    -0.07
     Accuracy
    -0.07
    POSITIVE LOGITS
     badges
    0.07
    想着
    0.07
     Budapest
    0.07
    二楼
    0.07
     gdzie
    0.07
    侁
    0.07
     Burn
    0.07
    :boolean
    0.07
     três
    0.07
    xDF
    0.07
    Act Density 0.034%

    No Known Activations