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

    Neuronpedia

    INDEX
    Explanations

    references to peace and its various forms and implications

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

    peace and peaceful variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manager
    -0.49
    Toronto
    -0.45
    From
    -0.42
     manipulator
    -0.42
    Hersteller
    -0.41
     DHS
    -0.41
     Hadid
    -0.40
     Supervisor
    -0.40
    yarnpkg
    -0.39
     wireType
    -0.39
    POSITIVE LOGITS
     PEACE
    1.25
     peace
    1.23
     Peace
    1.20
    peace
    1.18
    Peace
    1.16
    PEACE
    1.13
     peacefully
    0.87
     Peaceful
    0.86
    Peaceful
    0.83
     peaceful
    0.82
    Act Density 0.008%

    No Known Activations