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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lack
    0.56
     lacks
    0.55
    分け
    0.49
     hierarchy
    0.49
     uses
    0.48
    මෙ
    0.48
     બે
    0.47
     first
    0.47
     initially
    0.47
     bad
    0.47
    POSITIVE LOGITS
    <end_of_turn>
    0.73
     いつ
    0.72
    hydraz
    0.71
    <unused702>
    0.70
    <unused1701>
    0.69
    """.
    0.67
    <unused662>
    0.65
    ত্যাগ
    0.65
    <unused351>
    0.65
    <unused216>
    0.65
    Act Density 2.627%

    No Known Activations