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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rating
    -0.08
    ‥
    -0.07
     בעבר
    -0.07
    扫一扫
    -0.07
     następ
    -0.07
     accused
    -0.06
    قدر
    -0.06
    复兴
    -0.06
     breve
    -0.06
    웠
    -0.06
    POSITIVE LOGITS
    deque
    0.08
    constant
    0.07
    =config
    0.07
    始终
    0.07
    kich
    0.07
    Avoid
    0.06
     fragrance
    0.06
    death
    0.06
    _scan
    0.06
    plugin
    0.06
    Act Density 0.017%

    No Known Activations