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

    Neuronpedia

    INDEX
    Explanations

    instances of the French prefix "dé" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ans
    -0.14
    prar
    -0.14
    heard
    -0.14
    cola
    -0.14
    kol
    -0.14
    ints
    -0.14
    LOT
    -0.13
    reetings
    -0.13
    idf
    -0.13
    tü
    -0.13
    POSITIVE LOGITS
    amb
    0.19
    athlon
    0.16
    ron
    0.16
    anton
    0.15
    hou
    0.15
    mar
    0.15
    orent
    0.15
    mit
    0.14
    orm
    0.14
    name
    0.14
    Act Density 0.006%

    No Known Activations