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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =='
    0.54
     שהוא
    0.52
     Geschwindigkeit
    0.49
    ='
    0.48
    .
    0.47
    Iter
    0.46
     את
    0.45
    )[[
    0.45
    transition
    0.45
    test
    0.43
    POSITIVE LOGITS
     föret
    0.51
     pronta
    0.51
     novos
    0.50
    鎊
    0.48
     americano
    0.47
     corporations
    0.47
     certos
    0.47
     pouches
    0.46
    δία
    0.46
    ندق
    0.46
    Act Density 0.001%

    No Known Activations