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

    Neuronpedia

    INDEX
    Explanations

    a pattern related to various characters and symbols, potentially indicating a specific coding language or encryption method

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.74
    ĸļ
    -0.68
    atche
    -0.65
    ĪĴ
    -0.64
     parchment
    -0.60
     hole
    -0.59
     solicit
    -0.59
     motel
    -0.59
    ogyn
    -0.58
    hole
    -0.58
    POSITIVE LOGITS
    luster
    0.83
    ij士
    0.73
    gage
    0.70
    idated
    0.70
    atoes
    0.69
    ilot
    0.69
    rations
    0.67
    rano
    0.67
    hesda
    0.67
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    Act Density 0.353%

    No Known Activations