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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     HCI
    -0.07
    苔
    -0.07
    .setTime
    -0.07
    默
    -0.06
     bye
    -0.06
     Pawn
    -0.06
     �
    -0.06
     spir
    -0.06
     tread
    -0.06
    兹
    -0.06
    POSITIVE LOGITS
    有助于
    0.08
    реш
    0.08
     Billy
    0.07
    などの
    0.07
    utorials
    0.07
     unsere
    0.07
    之意
    0.07
    聊聊
    0.07
    ша
    0.07
    相关部门
    0.07
    Act Density 0.002%

    No Known Activations