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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tracks
    0.81
    ات
    0.80
    track
    0.78
    telling
    0.74
    想象
    0.73
    transcript
    0.71
    socks
    0.71
    suggestions
    0.71
    trap
    0.71
    s
    0.71
    POSITIVE LOGITS
     embora
    0.95
     Zuge
    0.89
     adegu
    0.88
     Versicherung
    0.86
     adanya
    0.86
     terminated
    0.84
     freund
    0.83
     Crore
    0.83
    ó
    0.82
     Schwarz
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.