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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    [label
    -0.08
    瞬间
    -0.08
     MetroFramework
    -0.08
    .Atoi
    -0.07
     있어
    -0.07
     disciples
    -0.07
    .To
    -0.07
     nationwide
    -0.07
     focused
    -0.07
     transporting
    -0.07
    POSITIVE LOGITS
     бумаг
    0.07
     tablespoon
    0.07
    זן
    0.07
    /output
    0.07
    jan
    0.07
    אוק
    0.07
    ム
    0.07
    鱼
    0.06
    Pow
    0.06
    홑
    0.06
    Act Density 0.006%

    No Known Activations