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

    Neuronpedia

    INDEX
    Explanations

    occurrences of violent actions and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sword
    -0.16
     bombed
    -0.15
    ROL
    -0.15
    dden
    -0.15
     rubbing
    -0.15
     guns
    -0.15
     Guns
    -0.15
     Rub
    -0.15
     tart
    -0.14
    ault
    -0.14
    POSITIVE LOGITS
     wounds
    0.23
     perfor
    0.22
     misses
    0.22
     grazing
    0.21
     wound
    0.21
     fired
    0.21
     rico
    0.20
     bullet
    0.20
     fatally
    0.20
     aimed
    0.20
    Act Density 0.096%

    No Known Activations