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

    Neuronpedia

    INDEX
    Explanations

    references to war or military conflicts

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

    war or Anwar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cecilia
    -0.54
    BASEPATH
    -0.52
    Rico
    -0.51
    PickerController
    -0.50
    oulli
    -0.49
     Cecilia
    -0.48
    tine
    -0.47
    濟
    -0.46
    cipline
    -0.46
     Lucio
    -0.46
    POSITIVE LOGITS
    war
    2.83
    WAR
    2.11
     war
    2.03
    War
    1.87
     WAR
    1.80
     War
    1.75
    wars
    1.62
    wara
    1.27
     wars
    1.25
     guerra
    1.25
    Act Density 0.009%

    No Known Activations