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

    Neuronpedia

    INDEX
    Explanations

    references to specific terms related to locations and groups, particularly those associated with certain named organizations or territories

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or entities related to Al-Madinah or similar names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Titanic
    -0.66
     Wilde
    -0.66
     Columbus
    -0.64
     Polar
    -0.64
     Victoria
    -0.63
     Poles
    -0.62
     Chloe
    -0.62
     Laur
    -0.61
     PV
    -0.61
     SPD
    -0.60
    POSITIVE LOGITS
    azeera
    1.46
    aeda
    1.20
    abi
    1.18
    aba
    1.18
    awi
    1.18
    aq
    1.07
    qqa
    1.06
    raq
    1.03
    aghd
    1.00
    aida
    1.00
    Act Density 0.049%

    No Known Activations