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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating imminent danger or high-stakes situations

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

    imminent danger or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retired
    -0.44
    retired
    -0.41
     retire
    -0.36
     Retired
    -0.36
    Retired
    -0.35
     retirement
    -0.35
    retirement
    -0.33
     Retire
    -0.32
     حق
    -0.30
    引退
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.75
     ModelExpression
    0.71
     autorytatywna
    0.70
    setVerticalGroup
    0.65
     незавершена
    0.63
    隨時
    0.62
     MutableLiveData
    0.61
     дописавши
    0.60
     '\\;'
    0.60
    awtextra
    0.59
    Act Density 0.072%

    No Known Activations