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

    Neuronpedia

    INDEX
    Explanations

    mentions of military actions and geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umi
    -0.14
     doma
    -0.14
    <tag
    -0.14
    undry
    -0.13
    uktur
    -0.13
    ê¶ģ
    -0.13
    ometown
    -0.13
    reet
    -0.13
    eder
    -0.13
    iamond
    -0.12
    POSITIVE LOGITS
     aggression
    0.34
     provoc
    0.32
     invasion
    0.32
     provocative
    0.31
     prov
    0.30
     annex
    0.28
     aggressive
    0.28
    ä¾µ
    0.27
     Prov
    0.27
     invade
    0.26
    Act Density 0.082%

    No Known Activations