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

    Neuronpedia

    INDEX
    Explanations

    file sizes mentioned in kilobytes

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to data size or file measurements, specifically in kilobytes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.74
     Fou
    -0.69
     charg
    -0.69
     celebr
    -0.66
     festivals
    -0.66
     Iran
    -0.65
     festival
    -0.65
     Iranian
    -0.65
    Hom
    -0.63
     Dante
    -0.63
    POSITIVE LOGITS
     KB
    4.19
    KB
    2.69
    kb
    2.03
     kb
    1.57
    kB
    1.21
     KM
    1.17
     WB
    1.15
    KC
    1.14
     KP
    1.12
     WP
    1.10
    Act Density 0.024%

    No Known Activations