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

    Neuronpedia

    INDEX
    Explanations

    references to American-related entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "American."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.83
    razil
    -0.70
    NB
    -0.69
    Prev
    -0.67
    RH
    -0.66
    flush
    -0.65
    */(
    -0.64
    ÃŁ
    -0.64
    orders
    -0.64
    ault
    -0.64
    POSITIVE LOGITS
     Airlines
    1.21
     Idol
    1.12
     Samoa
    1.12
    ICAN
    1.01
     Express
    0.92
     Legion
    0.89
    ized
    0.88
     Dream
    0.87
    icus
    0.84
     Pie
    0.84
    Act Density 0.069%

    No Known Activations