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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ενός
    0.51
     Peace
    0.44
    Peace
    0.43
     opponents
    0.42
     lambs
    0.42
     secrete
    0.42
    ills
    0.41
     spectacles
    0.41
     lenses
    0.40
     railings
    0.40
    POSITIVE LOGITS
    熱
    0.46
    딩
    0.44
    🏒
    0.43
     interven
    0.42
     moest
    0.41
    即使
    0.40
     доктор
    0.40
    अस
    0.40
    接触
    0.40
    退
    0.39
    Act Density 0.002%

    No Known Activations