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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with war

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citoy
    -0.90
    ภัณฑ์
    -0.80
    ClientSize
    -0.77
    ؤلاء
    -0.72
     policiales
    -0.72
     تضيفلها
    -0.72
    elsa
    -0.70
    reicht
    -0.70
    łaści
    -0.68
     gepf
    -0.68
    POSITIVE LOGITS
     war
    2.66
     War
    2.52
     WAR
    2.37
    War
    2.32
    war
    2.20
    WAR
    2.00
     wars
    1.94
     guerra
    1.76
     Wars
    1.60
    Wars
    1.57
    Act Density 0.079%

    No Known Activations