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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nutí
    0.51
    乐观
    0.47
    分裂
    0.46
    焦虑
    0.45
    二百
    0.42
    传统
    0.42
    临床
    0.42
    Issuer
    0.42
    漂
    0.42
     Dự
    0.41
    POSITIVE LOGITS
     garis
    0.54
     simonsen
    0.50
     palm
    0.50
     ran
    0.49
     possui
    0.49
     trainer
    0.49
     alis
    0.48
     fawn
    0.47
     diberi
    0.47
     estavam
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.