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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to duration and waiting

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

    how long something lasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBarButtonItem
    -0.51
    MLLoader
    -0.47
    dieu
    -0.45
    thâu
    -0.45
     تضيفلها
    -0.43
     للاسماء
    -0.40
     Commen
    -0.40
    IVEREF
    -0.40
     ویکی‌آمباردا
    -0.39
     الحره
    -0.38
    POSITIVE LOGITS
     lasted
    0.68
     stay
    0.64
     lasts
    0.62
     waited
    0.60
    duration
    0.60
     duration
    0.59
     stayed
    0.58
     wait
    0.57
     estuvo
    0.56
     durar
    0.56
    Act Density 0.029%

    No Known Activations