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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cursed
    0.41
     curse
    0.40
     😀
    0.40
     😄
    0.39
     hurried
    0.39
    !).
    0.39
     😊
    0.39
     चाहें
    0.39
     🙂
    0.38
     stink
    0.38
    POSITIVE LOGITS
     '">'
    0.42
    组件
    0.40
    тового
    0.40
    гази
    0.39
    Jennifer
    0.39
    Yeni
    0.38
     компонентов
    0.38
     যোগ
    0.38
    :'#
    0.37
    ioxide
    0.37
    Act Density 0.000%

    No Known Activations