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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Muslim" or references to the Muslim community

    oai_token-act-pair · gpt-3.5-turbo

    references to the Muslim community and its related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rive
    -0.72
    vable
    -0.68
    ately
    -0.66
    rarily
    -0.64
    TOP
    -0.64
    ellation
    -0.64
    ente
    -0.64
    wikipedia
    -0.63
    angled
    -0.62
    erick
    -0.62
    POSITIVE LOGITS
     Brotherhood
    1.35
     cleric
    1.02
    abad
    0.99
     clerics
    0.98
    majority
    0.98
    istani
    0.97
    ophobic
    0.91
    ophobia
    0.87
     supremacist
    0.86
     fundamentalist
    0.86
    Act Density 0.044%

    No Known Activations