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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     shores
    -0.07
     criminals
    -0.07
     اخت
    -0.07
    .INT
    -0.07
     chute
    -0.07
    禹
    -0.07
     המדינה
    -0.07
     الناس
    -0.06
    (Player
    -0.06
     fácil
    -0.06
    POSITIVE LOGITS
    .Quad
    0.07
    是中国
    0.07
    撸
    0.07
    露天
    0.06
     Learned
    0.06
    关键词
    0.06
     Quad
    0.06
    骒
    0.06
    =df
    0.06
     complement
    0.06
    Act Density 0.027%

    No Known Activations