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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gunmen
    -0.07
    同等
    -0.07
    墩
    -0.07
     bench
    -0.07
    Battle
    -0.07
     remind
    -0.07
     initData
    -0.07
     Token
    -0.07
    -girl
    -0.07
     Puppy
    -0.07
    POSITIVE LOGITS
     Networks
    0.07
    ᄋ
    0.07
    -style
    0.06
    村落
    0.06
    蚣
    0.06
     transformed
    0.06
     Moore
    0.06
    ologists
    0.06
    无视
    0.06
     Cart
    0.06
    Act Density 0.049%

    No Known Activations