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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    一句话
    -0.08
    报记者
    -0.07
    怎么回事
    -0.07
     demonstrated
    -0.07
     demonstrates
    -0.07
    ız
    -0.07
     WLAN
    -0.07
    <Project
    -0.07
    -[
    -0.06
     systematically
    -0.06
    POSITIVE LOGITS
    fell
    0.07
     sheds
    0.07
    ｵ
    0.07
     seal
    0.07
     Cinder
    0.06
    约束
    0.06
    消极
    0.06
    ביא
    0.06
    �
    0.06
    绢
    0.06
    Act Density 0.161%

    No Known Activations