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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    allet
    -0.07
     Edition
    -0.07
    某些
    -0.07
     poets
    -0.07
    鳍
    -0.07
    .category
    -0.07
     invited
    -0.07
     accents
    -0.06
    pls
    -0.06
     sofa
    -0.06
    POSITIVE LOGITS
    Ӏ
    0.07
    篼
    0.07
     birka
    0.07
    毌
    0.06
     Trọng
    0.06
    苤
    0.06
    .DeepEqual
    0.06
    _SAMPLE
    0.06
     bądź
    0.06
     ilçe
    0.06
    Act Density 0.001%

    No Known Activations