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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ತು
    1.06
    ား
    1.05
     Chambers
    1.01
     doss
    1.00
     weder
    0.99
    途径
    0.97
    Ɔ
    0.96
    ෙන්ම
    0.95
    我们的
    0.95
    Unsere
    0.94
    POSITIVE LOGITS
    이
    1.30
    ০
    1.25
     symbolize
    1.23
    ing
    1.22
     жало
    1.21
     liked
    1.17
    т
    1.17
    د
    1.15
    ت
    1.15
     spoiler
    1.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.