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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    轸
    0.72
     nowrap
    0.71
     fidelity
    0.71
    ពិស
    0.69
     Wester
    0.69
    Endian
    0.68
     Zed
    0.67
    ய்ய
    0.66
    ྱ
    0.66
    āda
    0.66
    POSITIVE LOGITS
    自动
    2.24
     automatic
    2.16
    Automatic
    2.15
     automaticamente
    2.14
     automatically
    2.13
    自動
    2.11
     Automatic
    2.07
     automatisch
    2.04
     otomatis
    2.04
    Automatically
    2.02
    Act Density 1.129%

    No Known Activations