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

    Neuronpedia

    INDEX
    Explanations

    references to violence and conflict-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haps
    -0.17
     Cata
    -0.15
    PLICIT
    -0.14
    resco
    -0.14
    æk
    -0.14
    Ñħод
    -0.14
    InBackground
    -0.14
     Guantanamo
    -0.13
     TRANSACTION
    -0.13
    uple
    -0.13
    POSITIVE LOGITS
     violence
    0.41
     Violence
    0.32
    viol
    0.29
    Viol
    0.28
     violent
    0.28
    -viol
    0.27
     viol
    0.26
     disorder
    0.25
     unrest
    0.24
     riots
    0.24
    Act Density 0.231%

    No Known Activations