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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stop" and phrases indicating pauses or moments of halting in action

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

    stopping at times or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.67
    Personendaten
    -0.60
     وتسجيلات
    -0.59
    GEBURTSDATUM
    -0.58
    presto
    -0.57
    astify
    -0.57
    曖昧さ回避
    -0.57
    SequentialGroup
    -0.55
    eira
    -0.54
    出版年
    -0.54
    POSITIVE LOGITS
     stopping
    0.66
     stopped
    0.58
    stopping
    0.56
     stops
    0.56
     stop
    0.52
     Stopping
    0.52
     Stopped
    0.51
    Stopping
    0.50
    stopped
    0.50
     zatrzy
    0.50
    Act Density 0.040%

    No Known Activations