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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Размер
    0.46
     honom
    0.43
     сестра
    0.40
     vorhanden
    0.40
    commentaire
    0.39
     Comunidad
    0.39
     Tamaño
    0.39
     $=$
    0.39
     происхождения
    0.39
    自己的
    0.39
    POSITIVE LOGITS
    ↵
    0.62
     think
    0.51
    There
    0.50
    Again
    0.49
    While
    0.48
    However
    0.47
     crucially
    0.47
    ↵↵↵↵
    0.46
     However
    0.46
    Because
    0.46
    Act Density 1.870%

    No Known Activations