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

    Neuronpedia

    INDEX
    Explanations

    terms related to violence and its societal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amework
    -0.16
    esty
    -0.15
    .datas
    -0.15
    izar
    -0.15
    evice
    -0.15
    rowsable
    -0.15
     sqlCommand
    -0.15
    onas
    -0.14
     insults
    -0.14
    otas
    -0.14
    POSITIVE LOGITS
     kill
    0.25
     violence
    0.24
     killing
    0.21
     sad
    0.21
     kills
    0.20
    kill
    0.20
     justification
    0.18
     dispatch
    0.18
     Violence
    0.18
     killings
    0.17
    Act Density 0.304%

    No Known Activations