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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    van
    -0.07
    yu
    -0.07
    花园
    -0.07
     populist
    -0.07
     QLineEdit
    -0.07
    体现
    -0.06
    붕
    -0.06
     developer
    -0.06
    恋爱
    -0.06
    融合发展
    -0.06
    POSITIVE LOGITS
     triggers
    0.07
    势
    0.07
    锜
    0.06
    0.06
    _correct
    0.06
    (choices
    0.06
     eggs
    0.06
    .err
    0.06
     unfortunately
    0.06
    强者
    0.06
    Act Density 0.152%

    No Known Activations