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

    Neuronpedia

    INDEX
    Explanations

    references to American history and culture

    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
    areth
    -0.77
     councillors
    -0.75
    âĶĢ
    -0.74
    reon
    -0.67
     sched
    -0.66
     councillor
    -0.65
    GG
    -0.64
    TL
    -0.63
    .>>
    -0.63
    =>
    -0.63
    POSITIVE LOGITS
     American
    3.40
    American
    2.98
     Americans
    2.48
    Americans
    2.37
     AMER
    2.32
     americ
    2.20
     America
    2.09
    America
    1.88
     Canadian
    1.77
     Australian
    1.69
    Act Density 0.039%

    No Known Activations