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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ым
    0.93
    lında
    0.91
    ꧂
    0.89
     больш
    0.89
    ]]></
    0.88
    🍢
    0.87
     beerCount
    0.86
     vooraf
    0.86
    🕌
    0.86
    ܐ
    0.85
    POSITIVE LOGITS
    to
    0.83
    test
    0.79
    tab
    0.79
    cos
    0.75
    date
    0.75
    custom
    0.74
    time
    0.74
     inactive
    0.74
    train
    0.73
    index
    0.73
    Act Density 0.000%

    No Known Activations