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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    응
    -0.09
    督
    -0.07
    amon
    -0.07
    .di
    -0.07
     comment
    -0.07
     !=
    -0.07
    ------
    -0.07
    複
    -0.07
    抗议
    -0.07
    _partitions
    -0.07
    POSITIVE LOGITS
     abilities
    0.07
    eliac
    0.07
    亲眼
    0.07
     Ear
    0.07
    lifetime
    0.07
     Cele
    0.07
     ABOUT
    0.07
    莫斯
    0.07
     Trouble
    0.07
     Bars
    0.07
    Act Density 0.011%

    No Known Activations