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

    Neuronpedia

    INDEX
    Explanations

    mentions of the city of Montreal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Montreal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -->
    -0.71
     Kush
    -0.69
    amsung
    -0.66
     bip
    -0.66
     jars
    -0.64
    oner
    -0.64
     recite
    -0.64
    */
    -0.63
     troop
    -0.63
     sidel
    -0.61
    POSITIVE LOGITS
     Montreal
    3.78
     Quebec
    2.48
     Ottawa
    2.20
     Winnipeg
    2.17
     Toronto
    2.16
     Edmonton
    2.15
     Vancouver
    2.14
    Toronto
    2.10
     Calgary
    2.10
     Canadiens
    2.08
    Act Density 0.011%

    No Known Activations