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

    Neuronpedia

    INDEX
    Explanations

    words related to physical violence

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocular
    -0.81
    heit
    -0.76
    sonian
    -0.76
    cellent
    -0.74
    STER
    -0.74
    obyl
    -0.73
    ļéĨĴ
    -0.72
    acent
    -0.72
    regon
    -0.72
    printed
    -0.71
    POSITIVE LOGITS
     violence
    0.93
     retribution
    0.89
     assault
    0.86
     suppression
    0.84
    acre
    0.82
     offenders
    0.81
     repression
    0.81
     retaliation
    0.80
     Islamist
    0.80
     clashes
    0.80
    Act Density 0.015%

    No Known Activations