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

    Neuronpedia

    INDEX
    Explanations

    references to actions or situations pertaining to peace or peaceful resolutions

    oai_token-act-pair · gpt-3.5-turbo

    references to peace and peacefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAC
    -0.91
    attr
    -0.80
    olog
    -0.78
    WD
    -0.76
    VM
    -0.74
    Sales
    -0.74
    ANA
    -0.73
    drivers
    -0.72
    odor
    -0.71
    aan
    -0.70
    POSITIVE LOGITS
     peaceful
    1.25
     peacefully
    1.01
     agre
    0.87
    peace
    0.86
     nonviolent
    0.83
    edIn
    0.81
     treaty
    0.78
     peace
    0.78
     minded
    0.78
     bystand
    0.78
    Act Density 0.006%

    No Known Activations