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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    </span>
    0.50
     fy
    0.48
     tell
    0.47
     probablement
    0.46
     gore
    0.45
     president
    0.45
     weren
    0.45
     frac
    0.44
     fact
    0.44
     common
    0.43
    POSITIVE LOGITS
     услу
    0.53
     искусства
    0.50
    ги
    0.48
    联
    0.47
    བ
    0.46
    ская
    0.46
     налого
    0.46
    тья
    0.45
     службы
    0.45
    Бу
    0.45
    Act Density 0.003%

    No Known Activations