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

    Neuronpedia

    INDEX
    Explanations

    descriptions and references to violent actions and killings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    602
    -0.16
    790
    -0.16
     Assault
    -0.16
    838
    -0.15
    lac
    -0.14
     recovery
    -0.14
    oped
    -0.14
    .Annotation
    -0.13
    934
    -0.13
    atan
    -0.13
    POSITIVE LOGITS
    /exec
    0.15
    errat
    0.15
    æº
    0.15
    ligne
    0.15
     Ful
    0.14
     kill
    0.14
     æŃ
    0.14
    kills
    0.14
    ада
    0.14
     kills
    0.14
    Act Density 0.179%

    No Known Activations