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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bottlenecks
    0.78
     warns
    0.76
     lurking
    0.75
     ständig
    0.74
     dialects
    0.73
     gefähr
    0.73
     adventurous
    0.72
    !
    0.72
     customers
    0.71
     excursions
    0.71
    POSITIVE LOGITS
     grieving
    1.42
     grief
    1.41
     mourning
    1.37
     grieve
    1.32
     Grief
    1.24
     funeral
    1.23
    悼
    1.21
     शोक
    1.20
     trauer
    1.19
     bereavement
    1.17
    Act Density 0.521%

    No Known Activations