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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    invest
    -0.08
    (delete
    -0.07
    ⚜
    -0.07
    ["_
    -0.07
    illing
    -0.07
    >).
    -0.07
    ,'%
    -0.07
    ıyor
    -0.06
    迢
    -0.06
     noodles
    -0.06
    POSITIVE LOGITS
    首创
    0.07
     Employee
    0.07
     Laugh
    0.07
    力争
    0.07
    十九
    0.06
    ҕ
    0.06
    ㈪
    0.06
    .pr
    0.06
    至上
    0.06
    쏟
    0.06
    Act Density 0.001%

    No Known Activations