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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enough
    1.06
    Enough
    0.96
    enough
    0.90
     genug
    0.89
     genoeg
    0.87
     Enough
    0.84
    夠
    0.57
    より
    0.53
    够
    0.52
    足够
    0.51
    POSITIVE LOGITS
     indeed
    0.59
     Indeed
    0.55
    indeed
    0.50
     뭐라고
    0.46
     imaginable
    0.44
    )}$
    0.44
    ola
    0.42
     تقریباً
    0.39
    idia
    0.38
     (~
    0.38
    Act Density 0.056%

    No Known Activations