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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location, namely New Orleans

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of New Orleans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ³
    -0.76
    ischer
    -0.75
    BOOK
    -0.74
    ãĤ¯
    -0.72
    OTHER
    -0.70
    ship
    -0.69
    ULE
    -0.67
    clock
    -0.67
    icial
    -0.66
    sch
    -0.65
    POSITIVE LOGITS
     Pelicans
    1.15
     Saints
    0.87
     Parish
    0.86
     Orleans
    0.82
    leans
    0.78
    boro
    0.76
     Brass
    0.72
     Angeles
    0.70
    ois
    0.69
    ques
    0.68
    Act Density 0.006%

    No Known Activations