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

    Neuronpedia

    INDEX
    Explanations

    references to quotes and citations from notable figures or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.71
    ſelf
    -0.63
     pleaſure
    -0.62
     Reſ
    -0.61
     ſind
    -0.60
     purpoſe
    -0.59
     leaſt
    -0.58
     Chriftian
    -0.57
     queſta
    -0.57
    TypedDataSet
    -0.56
    POSITIVE LOGITS
     مُعرِّف
    0.33
     Drapeau
    0.31
    UDES
    0.31
     Einstein
    0.31
     sł
    0.31
    utar
    0.30
    ky
    0.30
    ahar
    0.30
     quote
    0.29
    válasz
    0.29
    Act Density 0.056%

    No Known Activations