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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bif
    -0.07
    :e
    -0.07
    签署
    -0.07
    疥
    -0.07
    diği
    -0.07
    宽松
    -0.07
    <textarea
    -0.07
     generalized
    -0.07
    .say
    -0.07
    .Nome
    -0.07
    POSITIVE LOGITS
    汽车产业
    0.08
     timestep
    0.08
    火焰
    0.08
     ülkeler
    0.07
    ='_
    0.07
    车企
    0.07
     novelist
    0.07
    =>$
    0.07
    新闻网
    0.07
    石油
    0.07
    Act Density 0.001%

    No Known Activations