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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or dependencies in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    when a particle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.47
     pleaſure
    -0.43
     houſe
    -0.43
     pymysql
    -0.41
     ſtate
    -0.41
    ſelf
    -0.40
     ſch
    -0.40
     Inſ
    -0.39
     fubject
    -0.39
     Chriftian
    -0.38
    POSITIVE LOGITS
     üzere
    0.63
    해서
    0.62
    하여
    0.59
    ğinde
    0.57
    되어
    0.56
     따라
    0.54
     대해
    0.53
     dolayı
    0.53
    めて
    0.53
    年に
    0.52
    Act Density 0.011%

    No Known Activations