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

    Neuronpedia

    INDEX
    Explanations

    references to religious institutions, specifically mosques

    oai_token-act-pair · gpt-3.5-turbo

    references to mosques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.77
     Rockefeller
    -0.70
    lass
    -0.68
     Appalachian
    -0.67
    laus
    -0.65
    AW
    -0.64
    å¦
    -0.64
    lust
    -0.64
    short
    -0.64
    dit
    -0.64
    POSITIVE LOGITS
     mosque
    1.05
    abad
    1.02
     mosques
    0.95
     loudspe
    0.92
     cleric
    0.87
     Mosque
    0.86
    istani
    0.82
     prayer
    0.81
    hammad
    0.81
    zai
    0.79
    Act Density 0.013%

    No Known Activations