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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    +++
    -0.09
    奖学
    -0.07
    这样的话
    -0.07
     lassen
    -0.07
    field
    -0.07
     meals
    -0.07
    exist
    -0.07
     boon
    -0.07
     Xin
    -0.07
    いました
    -0.07
    POSITIVE LOGITS
    처
    0.07
    瑛
    0.06
     chances
    0.06
     theor
    0.06
    𝑡
    0.06
    (status
    0.06
     thyroid
    0.06
    _theta
    0.06
     plat
    0.06
     ###↵
    0.06
    Act Density 0.028%

    No Known Activations