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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .commit
    -0.08
     сильно
    -0.07
    证书
    -0.07
    Torrent
    -0.07
    顼
    -0.07
     admitted
    -0.07
    udden
    -0.07
    一根
    -0.07
    不慎
    -0.07
    深
    -0.07
    POSITIVE LOGITS
     Gameplay
    0.07
    fall
    0.06
     Hick
    0.06
     agility
    0.06
     Scal
    0.06
     BW
    0.06
     upcoming
    0.06
     ld
    0.06
     millennia
    0.06
     năng
    0.06
    Act Density 0.006%

    No Known Activations