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

    Neuronpedia

    INDEX
    Explanations

    specific mentions or descriptions of a sizable or significant amount of something

    oai_token-act-pair · gpt-3.5-turbo

    references to large portions or segments of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parade
    -0.70
     Examiner
    -0.65
    Adv
    -0.65
    ggles
    -0.65
     Correspond
    -0.62
    ENCE
    -0.61
    CV
    -0.61
    ggies
    -0.60
    adv
    -0.60
     FANTASY
    -0.59
    POSITIVE LOGITS
    meal
    1.11
     chunks
    1.08
    iest
    0.94
     chunk
    0.88
    staking
    0.83
    eenth
    0.83
    paste
    0.80
    alm
    0.79
    efully
    0.79
    ies
    0.78
    Act Density 0.019%

    No Known Activations