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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating achievements or impressive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urrect
    -0.14
    799
    -0.14
     feliz
    -0.14
     dear
    -0.14
     annoying
    -0.13
    ifest
    -0.13
     Ups
    -0.13
     lekker
    -0.13
     aroma
    -0.13
     incons
    -0.13
    POSITIVE LOGITS
     impressive
    0.44
     impress
    0.41
     awe
    0.35
     impres
    0.35
     remarkable
    0.35
     amazing
    0.34
     incredible
    0.34
     impression
    0.33
     impressed
    0.32
    Amazing
    0.31
    Act Density 0.328%

    No Known Activations