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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.95
    年中
    0.92
    蹤
    0.89
    ച്ചി
    0.89
    Touches
    0.89
    申し込み
    0.87
    尺寸
    0.87
    owntown
    0.86
    uncur
    0.86
     шесть
    0.86
    POSITIVE LOGITS
     societal
    1.44
     fucked
    1.42
     shitty
    1.41
     incentiv
    1.35
     society
    1.24
     corrupt
    1.24
     corruption
    1.23
     detrimental
    1.23
     fucking
    1.23
     stagn
    1.22
    Act Density 0.488%

    No Known Activations