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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atter
    -0.07
     Duterte
    -0.07
    黑暗
    -0.07
    etect
    -0.07
    etto
    -0.07
    ками
    -0.07
     couples
    -0.07
    污染
    -0.06
     גר
    -0.06
    clist
    -0.06
    POSITIVE LOGITS
    '},↵
    0.08
     Trường
    0.07
    쎼
    0.07
    Nested
    0.07
    _Obj
    0.07
    ＝
    0.06
    Prot
    0.06
    也不是
    0.06
    ꪋ
    0.06
    )._
    0.06
    Act Density 0.104%

    No Known Activations