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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Terminal
    -0.08
    Art
    -0.07
    脑海
    -0.07
     pkg
    -0.07
    另一种
    -0.06
    Andy
    -0.06
    艟
    -0.06
     mailbox
    -0.06
     `-
    -0.06
     Universität
    -0.06
    POSITIVE LOGITS
    SOURCE
    0.07
    .equals
    0.07
    去找
    0.07
    因果
    0.07
     incentives
    0.07
    _sequences
    0.07
    转型升级
    0.06
    利润
    0.06
    各县
    0.06
    -directed
    0.06
    Act Density 0.039%

    No Known Activations