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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases indicating military or geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /of
    -0.15
    /or
    -0.14
    exampleInput
    -0.13
     foregoing
    -0.13
    urt
    -0.13
    wards
    -0.12
    ạnh
    -0.12
     outset
    -0.12
    ®,
    -0.12
    -Compatible
    -0.12
    POSITIVE LOGITS
     which
    0.20
     któ
    0.18
     whom
    0.18
     ìĿ´ëĬĶ
    0.17
     denen
    0.17
     który
    0.17
    issant
    0.16
     notamment
    0.15
    ché
    0.15
     cuales
    0.15
    Act Density 0.906%

    No Known Activations