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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    尚书
    -0.08
    頻
    -0.08
     activist
    -0.07
    如果你
    -0.07
    fsp
    -0.07
    utt
    -0.07
     inclusive
    -0.07
    以上的
    -0.07
    Coeff
    -0.07
     Soph
    -0.07
    POSITIVE LOGITS
    اعتم
    0.07
    긷
    0.07
     Contracts
    0.07
    \Entities
    0.07
    แผ
    0.07
     mediums
    0.06
    实行
    0.06
     aggrav
    0.06
    엮
    0.06
    ('_',
    0.06
    Act Density 0.026%

    No Known Activations