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

    Neuronpedia

    INDEX
    Explanations

    references to terrorist activities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various terrorist groups and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Herald
    -0.70
     Wind
    -0.67
    Solar
    -0.65
    à¤
    -0.64
    Coun
    -0.64
    CHECK
    -0.63
     Labor
    -0.63
    orse
    -0.62
     Life
    -0.62
    Wind
    -0.62
    POSITIVE LOGITS
    ervatives
    1.17
    aurus
    1.17
    ervative
    1.12
    hip
    1.07
    paces
    0.97
    ']
    0.92
    '
    0.88
    wana
    0.88
    hips
    0.87
    anamo
    0.85
    Act Density 0.067%

    No Known Activations