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

    Neuronpedia

    INDEX
    Explanations

    terms related to violence and conflict, particularly involving attacks and weaponry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pingback
    -0.59
    hljs
    -0.58
    IBar
    -0.57
     îng
    -0.56
     Wallflower
    -0.56
    ViewFeatures
    -0.56
     GetEnumerator
    -0.56
    conductivity
    -0.55
     समीक्षाओं
    -0.54
    Historique
    -0.54
    POSITIVE LOGITS
     attack
    1.17
     attacking
    1.05
     Attack
    1.04
    attack
    1.02
     attacks
    1.01
    Attack
    0.96
     ATTACK
    0.94
     attacked
    0.93
     Attacks
    0.93
     Targeting
    0.90
    Act Density 0.491%

    No Known Activations