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

    Neuronpedia

    INDEX
    Explanations

    references to violence and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Killing
    -0.15
     quit
    -0.15
    Dead
    -0.15
     dead
    -0.14
    apon
    -0.14
    rani
    -0.14
    andalone
    -0.14
    acco
    -0.14
     evid
    -0.14
    asp
    -0.14
    POSITIVE LOGITS
     during
    0.21
     trying
    0.18
     by
    0.17
     when
    0.16
     while
    0.16
    during
    0.16
    eva
    0.15
     falling
    0.15
     During
    0.15
     attempting
    0.15
    Act Density 0.066%

    No Known Activations