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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ideshow
    -0.08
    ZZ
    -0.08
     FIRE
    -0.07
    朔
    -0.07
    舒
    -0.07
     stressed
    -0.07
     Chị
    -0.07
    _ui
    -0.07
    形
    -0.07
    雅
    -0.06
    POSITIVE LOGITS
     ++)↵
    0.07
    쯧
    0.07
    借口
    0.07
                                                ↵
    0.07
    喝水
    0.07
     Vân
    0.07
    าน
    0.06
    łoży
    0.06
    ")))↵
    0.06
    cych
    0.06
    Act Density 0.030%

    No Known Activations