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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more" and phrases indicating an increase or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eless
    -0.17
    üst
    -0.16
    orus
    -0.16
     вов
    -0.15
    episode
    -0.14
    isel
    -0.14
    kal
    -0.14
    Anim
    -0.14
    á½´
    -0.14
    uid
    -0.13
    POSITIVE LOGITS
    ált
    0.15
    inally
    0.15
    xDF
    0.14
    SETS
    0.14
    edor
    0.13
    jedn
    0.13
    alker
    0.13
    itage
    0.13
    StringUtil
    0.13
    λεκ
    0.12
    Act Density 0.180%

    No Known Activations