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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    0.59
    rH
    0.50
    o
    0.46
    0.46
    oy
    0.46
    r
    0.46
    e
    0.44
    y
    0.44
    re
    0.43
    aS
    0.43
    POSITIVE LOGITS
     порядка
    0.58
     of
    0.57
     သည်
    0.55
     нажа
    0.53
     ऑफ़
    0.53
     জনপ্রিয়তা
    0.52
     हीरे
    0.52
    וב
    0.50
     ngại
    0.49
     bystanders
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.