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

    Neuronpedia

    INDEX
    Explanations

    references to peace and peace-related initiatives or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Peace Prize Treaty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hadid
    -0.42
    发表于
    -0.41
    studium
    -0.41
     betweenstory
    -0.40
     Lombard
    -0.40
    principalTable
    -0.40
    دانشنامهٔ
    -0.39
     Italij
    -0.38
     виправивши
    -0.38
     typelib
    -0.38
    POSITIVE LOGITS
     Peace
    2.28
    Peace
    2.11
     PEACE
    1.79
    PEACE
    1.62
    peace
    1.61
     peace
    1.45
     Paz
    1.09
    Paz
    1.01
     paz
    1.00
     Peaceful
    0.96
    Act Density 0.009%

    No Known Activations