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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .uf
    -0.07
    ush
    -0.07
     역시
    -0.06
    ze
    -0.06
    ect
    -0.06
    وف
    -0.06
    来自于
    -0.06
    继续
    -0.06
    -f
    -0.06
    🐤
    -0.06
    POSITIVE LOGITS
    }↵
    0.07
     baths
    0.07
     закон
    0.07
    _SEQUENCE
    0.07
    衫
    0.06
    Walker
    0.06
    ಌ
    0.06
    苤
    0.06
     consciousness
    0.06
    	entity
    0.06
    Act Density 0.002%

    No Known Activations