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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions involving conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼ĭ
    -0.16
     blowing
    -0.16
     Blow
    -0.15
    anzi
    -0.15
     Architect
    -0.15
     blown
    -0.15
    çĤ¸
    -0.15
     Blink
    -0.14
    ento
    -0.14
    çĽijåIJ¬é¡µéĿ¢
    -0.14
    POSITIVE LOGITS
     lung
    0.28
     tackle
    0.26
     tackled
    0.25
     grabbed
    0.25
     grab
    0.23
    grab
    0.23
     tackling
    0.22
     pin
    0.22
     Grab
    0.22
     pinned
    0.22
    Act Density 0.135%

    No Known Activations