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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Cleaning
    -0.08
    -0.07
    ************************
    -0.07
     looked
    -0.07
    orget
    -0.07
    )]
↵
    -0.07
    各行各
    -0.07
                           ↵
    -0.07
    -0.07
     tra
    -0.07
    POSITIVE LOGITS
     obedience
    0.08
    非常明显
    0.08
    êu
    0.08
    坚硬
    0.08
    -names
    0.07
    Nome
    0.07
    ลาย
    0.07
    ussian
    0.07
    emia
    0.07
    \Cache
    0.07
    Act Density 0.024%

    No Known Activations