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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ော့
    0.57
     Magento
    0.53
     MacOS
    0.52
     linestyle
    0.51
     ಇನ್ನ
    0.49
     tmux
    0.49
     BatchNorm
    0.49
     ಅವರ
    0.48
     Lenovo
    0.48
     niego
    0.48
    POSITIVE LOGITS
     which
    0.93
     которые
    0.91
     that
    0.89
    —
    0.88
    which
    0.86
     които
    0.82
     које
    0.79
     που
    0.78
     koje
    0.77
     ซึ่ง
    0.76
    Act Density 1.313%

    No Known Activations