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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ו
    1.02
    i
    0.95
    ه
    0.88
    ers
    0.80
    es
    0.76
     Xi
    0.75
     entendu
    0.74
     I
    0.73
    e
    0.71
    ς
    0.71
    POSITIVE LOGITS
     ያል
    0.84
    ovascular
    0.79
    ありません
    0.79
     protested
    0.78
     aborted
    0.78
    क्राफ्ट
    0.78
     congratulated
    0.77
    на
    0.77
     attacked
    0.75
     orchestra
    0.75
    Act Density 0.000%

    No Known Activations