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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating goals, ambitions, and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Booster
    -0.16
     uplift
    -0.16
     boosted
    -0.15
     incl
    -0.14
    翼
    -0.13
     Chap
    -0.13
    olson
    -0.13
    appen
    -0.13
     inclusive
    -0.13
     benefited
    -0.13
    POSITIVE LOGITS
     provide
    0.20
    /Create
    0.20
    Provide
    0.20
    provide
    0.20
     Provide
    0.20
    æıIJä¾Ľ
    0.17
    /create
    0.17
     exceed
    0.17
     пÑĢедоÑģÑĤав
    0.16
    spread
    0.15
    Act Density 0.191%

    No Known Activations