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

    Neuronpedia

    INDEX
    Explanations

    mentions of the quantity "thousands"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.67
     ([
    -0.67
     fundament
    -0.66
    verages
    -0.65
    NES
    -0.65
    Prov
    -0.64
    acea
    -0.64
    anus
    -0.63
    imation
    -0.63
    liest
    -0.63
    POSITIVE LOGITS
     miles
    1.09
     pounds
    1.05
     thousands
    1.05
     acres
    1.03
     kilometers
    1.00
     dollars
    0.96
     hectares
    0.94
     kilometres
    0.94
     consecutive
    0.91
     kilograms
    0.89
    Act Density 0.063%

    No Known Activations