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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Amazing
    -0.07
     Triple
    -0.06
     instincts
    -0.06
     completes
    -0.06
    失落
    -0.06
    第一家
    -0.06
    𐰰
    -0.06
    初
    -0.06
     FString
    -0.06
    inition
    -0.06
    POSITIVE LOGITS
    сла
    0.08
    ledo
    0.07
    -comp
    0.07
     prostitute
    0.07
    ToDelete
    0.07
    too
    0.07
    محاولة
    0.07
     Decor
    0.06
    _OM
    0.06
    iéndo
    0.06
    Act Density 0.003%

    No Known Activations