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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "eg" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.17
    leck
    -0.16
    oir
    -0.16
     <|
    -0.15
    ACTER
    -0.15
     OnCollision
    -0.14
    ÑĤоÑĩ
    -0.14
    ãģĺ
    -0.14
    LANG
    -0.14
    chas
    -0.14
    POSITIVE LOGITS
     Eg
    0.23
     eg
    0.20
     egg
    0.20
     Egg
    0.20
    ads
    0.19
    bert
    0.17
     Eins
    0.17
    egg
    0.17
    ADS
    0.16
     Eggs
    0.16
    Act Density 0.015%

    No Known Activations