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

    Neuronpedia

    INDEX
    Explanations

    references to Islamic-related terms or topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Islamic law or the Islamic State

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.79
    butt
    -0.77
    ym
    -0.75
    brid
    -0.74
    laus
    -0.71
     WD
    -0.67
    eting
    -0.66
    shaw
    -0.65
    slice
    -0.65
    )=(
    -0.64
    POSITIVE LOGITS
    abad
    0.92
    ophobic
    0.92
     Islamic
    0.90
     cleric
    0.90
     Sharia
    0.90
     extremism
    0.87
    Islamic
    0.85
     Jihad
    0.83
     jihadist
    0.81
     suprem
    0.81
    Act Density 0.011%

    No Known Activations