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

    Neuronpedia

    INDEX
    Explanations

    references to war-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ClientSize
    -0.88
     يتيمه
    -0.79
     تضيفلها
    -0.78
    __":
    -0.74
     дописавши
    -0.69
    ؤلاء
    -0.68
    сылкі
    -0.67
    ANEOUS
    -0.67
     arşivlendi
    -0.66
     &___
    -0.65
    POSITIVE LOGITS
     War
    0.94
    War
    0.94
     WAR
    0.92
    war
    0.84
     war
    0.83
    WAR
    0.75
     guerra
    0.70
     Guerra
    0.62
    Guerra
    0.61
    Wars
    0.59
    Act Density 0.071%

    No Known Activations