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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ahead
    0.61
     Demonstrated
    0.59
     Another
    0.59
    ätte
    0.58
     Revealed
    0.58
     Source
    0.58
    できなかった
    0.57
     sebuah
    0.55
     ढाई
    0.55
     One
    0.55
    POSITIVE LOGITS
     keywords
    1.79
     searches
    1.74
    搜索
    1.73
     keyword
    1.70
    keywords
    1.63
     search
    1.62
    search
    1.59
    keyword
    1.56
    Search
    1.54
    关键词
    1.51
    Act Density 1.231%

    No Known Activations