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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "De" followed by a single letter, possibly related to names or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.71
     CPC
    -0.69
     Showdown
    -0.65
     Cobra
    -0.65
     exhibits
    -0.64
    ãĤ¤ãĥĪ
    -0.64
     Wage
    -0.62
    ĸļ
    -0.60
     Topics
    -0.60
     Dragonbound
    -0.60
    POSITIVE LOGITS
    arest
    1.25
    bris
    1.23
    legate
    1.22
    utsch
    1.21
    leted
    1.18
    legates
    1.18
    cember
    1.16
    classified
    1.12
    forestation
    1.12
    gradation
    1.06
    Act Density 0.035%

    No Known Activations