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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    刽
    -0.07
    紧跟
    -0.07
     Alv
    -0.07
     sooner
    -0.07
    闪光
    -0.07
     persever
    -0.07
     değerl
    -0.06
    ye
    -0.06
    _sl
    -0.06
    鄜
    -0.06
    POSITIVE LOGITS
    קס
    0.07
    Charlotte
    0.07
     Includes
    0.07
     tapped
    0.07
    נפתח
    0.07
    arring
    0.07
    mort
    0.07
    bled
    0.07
    同学
    0.07
    Order
    0.07
    Act Density 0.005%

    No Known Activations