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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Muslims"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Muslims."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATA
    -0.83
    æ©
    -0.74
     Rockefeller
    -0.72
    inventoryQuantity
    -0.72
     Vaugh
    -0.71
    cold
    -0.70
     Hoover
    -0.68
    amina
    -0.67
    FINE
    -0.67
     Nich
    -0.66
    POSITIVE LOGITS
    ophobic
    1.07
    ophobia
    1.01
    abad
    1.00
    hammad
    0.97
    istani
    0.95
    folk
    0.91
    alam
    0.82
    Muslims
    0.79
     Muslims
    0.79
    majority
    0.77
    Act Density 0.012%

    No Known Activations