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

    Neuronpedia

    INDEX
    Explanations

    references to civilian casualties and their implications in conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ameleon
    -0.17
    byss
    -0.16
    igin
    -0.16
     âm
    -0.15
    λοÏĤ
    -0.15
    oyer
    -0.15
     å½
    -0.15
    ãĥĥãĤ«ãĥ¼
    -0.14
    .Assembly
    -0.14
    ullen
    -0.14
    POSITIVE LOGITS
     bystand
    0.18
     innocent
    0.15
     innoc
    0.14
     civilians
    0.14
    259
    0.14
    izable
    0.14
     innocence
    0.14
    ighter
    0.14
    /small
    0.14
    å±ħ
    0.13
    Act Density 0.026%

    No Known Activations