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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵
    0.52
    ute
    0.51
    urer
    0.50
    noun
    0.48
    은
    0.48
    jpg
    0.47
     buckles
    0.46
    si
    0.46
    fry
    0.46
    expressions
    0.46
    POSITIVE LOGITS
    .[[
    0.55
     अशुभ
    0.52
    
    0.51
     забы
    0.50
     Gubern
    0.49
    }-[
    0.48
    alaikums
    0.48
     فونبټ
    0.48
     ရက်
    0.48
    <unused2013>
    0.48
    Act Density 0.000%

    No Known Activations