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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ഒന്ന്
    0.45
     रहीम
    0.39
     Think
    0.39
     Older
    0.39
    ເຕ
    0.39
    寄
    0.39
     bootstrapping
    0.38
    仓
    0.38
     Wilbur
    0.38
    柅
    0.38
    POSITIVE LOGITS
    Chain
    0.42
    peed
    0.41
    uer
    0.41
    uelto
    0.41
     सफलता
    0.40
     bras
    0.39
    Bras
    0.39
    Score
    0.39
    ervis
    0.39
    oteur
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.