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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    两次
    -0.07
    裹
    -0.07
     Seminar
    -0.07
    (Is
    -0.07
    _lex
    -0.07
     граждан
    -0.07
     Attend
    -0.07
    衡
    -0.06
    叁
    -0.06
    蕰
    -0.06
    POSITIVE LOGITS
    فحص
    0.07
     хоть
    0.07
    styleType
    0.07
    ’app
    0.07
    ает
    0.07
    ꀀ
    0.06
    ﯼ
    0.06
    ᅥ
    0.06
    ADF
    0.06
     Ukrainian
    0.06
    Act Density 0.004%

    No Known Activations