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

    Neuronpedia

    INDEX
    Explanations

    references to police actions and the use of force

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å·»
    -0.15
    гов
    -0.15
    çĿĽ
    -0.14
    loff
    -0.14
    amage
    -0.14
    hů
    -0.14
    ermint
    -0.14
    _APB
    -0.13
    ieux
    -0.13
     Wish
    -0.13
    POSITIVE LOGITS
     pepper
    0.33
     TAS
    0.33
     Tas
    0.32
     tas
    0.30
     Pepper
    0.29
     bat
    0.28
    tas
    0.28
     stun
    0.27
     tear
    0.23
     Tear
    0.23
    Act Density 0.041%

    No Known Activations