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

    Neuronpedia

    INDEX
    Explanations

    mentions of the letter "K" with accompanying numerical values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "K" followed by numeric values, likely indicating a reference to something specific or branded

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.73
    terday
    -0.73
     Polly
    -0.62
     Celest
    -0.61
     medieval
    -0.59
     ascending
    -0.59
     vested
    -0.59
     Yor
    -0.58
     letting
    -0.58
     repent
    -0.57
    POSITIVE LOGITS
    ittens
    1.20
    udos
    1.20
    ernels
    1.19
    razy
    1.15
    ratom
    1.15
    rieg
    1.14
    EEP
    1.13
    nee
    1.13
    ettle
    1.12
    aspers
    1.12
    Act Density 0.035%

    No Known Activations