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

    Neuronpedia

    INDEX
    Explanations

    mentions of American identity and opinions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Americans and their perspectives or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.68
    inventoryQuantity
    -0.66
    ologies
    -0.65
    cer
    -0.65
    type
    -0.63
    rament
    -0.63
     NEC
    -0.63
    bol
    -0.63
    selection
    -0.62
    POR
    -0.61
    POSITIVE LOGITS
     who
    0.88
     living
    0.85
    '
    0.85
     residing
    0.80
    hip
    0.79
     tuned
    0.77
     polled
    0.76
     aged
    0.74
     enjoying
    0.73
     watching
    0.73
    Act Density 0.082%

    No Known Activations