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

    Neuronpedia

    INDEX
    Explanations

    the word "chunk"

    oai_token-act-pair · gpt-3.5-turbo

    references to significant portions or segments of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parade
    -0.69
    CV
    -0.67
    Adv
    -0.64
     consultants
    -0.63
    ggies
    -0.63
    dinand
    -0.60
    gency
    -0.60
    pose
    -0.60
    adv
    -0.60
     Mood
    -0.59
    POSITIVE LOGITS
    meal
    0.96
     chunks
    0.89
     chunk
    0.84
    ridge
    0.82
    iest
    0.81
    eenth
    0.78
    buster
    0.76
    wit
    0.75
    nown
    0.74
    alm
    0.73
    Act Density 0.033%

    No Known Activations