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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    暴涨
    -0.07
    퍙
    -0.07
    模范
    -0.07
    会在
    -0.07
    北海
    -0.07
    -turned
    -0.06
     Prospect
    -0.06
     matching
    -0.06
    tığımız
    -0.06
    专栏
    -0.06
    POSITIVE LOGITS
    ew
    0.07
    û
    0.07
    ,↵↵
    0.07
    )↵↵
    0.07
    的事情
    0.07
     حقيقي
    0.07
    _objects
    0.06
    &e
    0.06
      
↵
↵
    0.06
    )
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.