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

    Neuronpedia

    INDEX
    Explanations

    references to coercive power and the role of violence in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡Å¥
    -0.15
    enemy
    -0.15
    ANTI
    -0.15
    SystemService
    -0.14
     sobie
    -0.14
    esty
    -0.14
     Enemies
    -0.14
     commod
    -0.14
    è§
    -0.14
    ãģĻãģĻ
    -0.13
    POSITIVE LOGITS
     force
    0.27
     violence
    0.25
     resort
    0.25
     techniques
    0.22
     methods
    0.22
     carrots
    0.22
     tactics
    0.22
     FORCE
    0.21
    -force
    0.21
     Force
    0.21
    Act Density 0.335%

    No Known Activations