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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sister
    -0.07
    tearDown
    -0.07
    home
    -0.07
     Group
    -0.07
     добав
    -0.07
     Bless
    -0.07
    дан
    -0.07
    Otherwise
    -0.07
     degree
    -0.06
    examples
    -0.06
    POSITIVE LOGITS
    哈登
    0.08
    的味道
    0.07
     tackle
    0.07
     scl
    0.07
    -wage
    0.07
    _API
    0.07
    委副书记
    0.07
    [param
    0.07
     eventData
    0.07
    )","
    0.07
    Act Density 0.003%

    No Known Activations