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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    below
    -0.07
    爬
    -0.07
                      ↵
    -0.07
     dat
    -0.07
    ^
    -0.07
    孩童
    -0.07
     parted
    -0.07
     total
    -0.07
    Categories
    -0.07
     cup
    -0.07
    POSITIVE LOGITS
    [js
    0.08
    Instr
    0.08
    安全管理
    0.08
     השא
    0.07
     Laf
    0.07
     Renderer
    0.07
    פעל
    0.07
    もし
    0.07
    Propagation
    0.07
    _Renderer
    0.07
    Act Density 0.006%

    No Known Activations