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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Axis
    -0.07
    (np
    -0.07
    有不少
    -0.07
    了一系列
    -0.07
    懷
    -0.07
    (chunk
    -0.07
    Career
    -0.06
    日讯
    -0.06
    Plug
    -0.06
    埋
    -0.06
    POSITIVE LOGITS
    ','');↵
    0.08
     defamation
    0.07
    虼
    0.07
     Ricky
    0.07
    变压
    0.07
    -san
    0.06
     ridiculous
    0.06
     unbelievable
    0.06
     componentName
    0.06
     hearty
    0.06
    Act Density 0.002%

    No Known Activations