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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "novel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "novel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.74
    henko
    -0.67
    zona
    -0.64
    olid
    -0.63
    adow
    -0.62
    tics
    -0.61
    poke
    -0.61
    older
    -0.61
    Downloadha
    -0.59
    ++++
    -0.59
    POSITIVE LOGITS
    ties
    1.12
    izations
    1.05
    isations
    1.04
    isation
    0.90
     manuscript
    0.87
     adaptation
    0.81
    ization
    0.81
    culosis
    0.81
    acters
    0.80
    uscript
    0.78
    Act Density 0.013%

    No Known Activations