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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance, often related to comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the degree or extent of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     STA
    -0.72
    ounded
    -0.69
    ersive
    -0.67
    aleb
    -0.66
     Compliance
    -0.64
    iets
    -0.64
    eele
    -0.63
    hua
    -0.62
    É
    -0.61
     Topics
    -0.61
    POSITIVE LOGITS
     imaginable
    1.26
    except
    0.96
     except
    0.96
     conceivable
    0.91
     nodd
    0.84
    nut
    0.77
     thereafter
    0.73
     sane
    0.72
     whatsoever
    0.72
    Except
    0.70
    Act Density 0.231%

    No Known Activations