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
     cut
    -0.07
     COL
    -0.07
     citing
    -0.07
    wash
    -0.07
     government
    -0.07
    咳
    -0.06
     knee
    -0.06
    COL
    -0.06
    延
    -0.06
    POSITIVE LOGITS
    Composer
    0.08
    zent
    0.07
    (update
    0.07
    /simple
    0.07
    Normalize
    0.07
    嘉兴
    0.07
    Plugins
    0.07
    되었다
    0.07
    =".
    0.07
    (IEnumerable
    0.06
    Act Density 0.002%

    No Known Activations