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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to international relations and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.80
     unless
    -0.74
    Usually
    -0.74
    é»Ĵ
    -0.73
    olitics
    -0.73
    Hopefully
    -0.73
    entimes
    -0.72
     thereof
    -0.72
    lopp
    -0.71
    NOW
    -0.71
    POSITIVE LOGITS
     Argentina
    0.91
     Angola
    0.89
     Yugoslavia
    0.89
     USS
    0.88
     Ronald
    0.87
     Algeria
    0.85
     Ferdinand
    0.84
     Bolivia
    0.84
     Chile
    0.82
     Tanzania
    0.82
    Act Density 0.598%

    No Known Activations