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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ease of use or simplicity

    oai_token-act-pair · gpt-3.5-turbo

    references to ease of use or usability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psey
    -0.68
    forth
    -0.66
    orp
    -0.66
    ¬¼
    -0.63
     teasp
    -0.62
    letters
    -0.61
    Bet
    -0.60
    azo
    -0.60
     Literary
    -0.59
    aleb
    -0.58
    POSITIVE LOGITS
     manoeuv
    0.76
    aic
    0.67
     MPG
    0.65
     setups
    0.65
    craft
    0.63
    efficient
    0.63
    ament
    0.63
    expensive
    0.63
    */(
    0.63
    ugu
    0.62
    Act Density 0.178%

    No Known Activations