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

    Neuronpedia

    INDEX
    Explanations

    specific nationalities or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities, particularly Germans and Russians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.71
    antha
    -0.68
    Ear
    -0.68
    tains
    -0.68
    acts
    -0.67
    amia
    -0.66
    VIEW
    -0.66
    ģ«
    -0.65
    paragraph
    -0.65
    azines
    -0.64
    POSITIVE LOGITS
    ervative
    0.82
     themselves
    0.80
    layer
    0.78
    '
    0.77
    folk
    0.74
     wisely
    0.73
     weren
    0.71
    ervatives
    0.69
    ons
    0.65
    linger
    0.64
    Act Density 0.166%

    No Known Activations