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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cells
    0.46
    И
    0.45
    輸
    0.45
    М
    0.45
    omorphic
    0.44
    R
    0.43
    Grace
    0.43
    header
    0.42
    Margin
    0.42
    S
    0.42
    POSITIVE LOGITS
     destru
    0.55
     impunity
    0.52
     democracy
    0.50
     obey
    0.48
     desesper
    0.47
     unlaw
    0.47
     lebt
    0.47
     destroying
    0.46
     destruction
    0.45
     treason
    0.45
    Act Density 0.001%

    No Known Activations