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

    Neuronpedia

    INDEX
    Explanations

    words related to computing, such as 'computer', 'science', 'images', 'website', 'Registar', and terms like 'personal expenditure' and 'enrollment'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "pt" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CE
    -0.79
     resil
    -0.72
    çĶ°
    -0.67
    ATIVE
    -0.64
    ISH
    -0.62
    CLOSE
    -0.61
    beit
    -0.61
    hold
    -0.60
    IRO
    -0.60
    WAY
    -0.60
    POSITIVE LOGITS
    itude
    1.14
    ember
    1.11
    acular
    1.09
    icket
    1.01
    uple
    0.97
    itudes
    0.92
    eous
    0.92
    eenth
    0.90
    unia
    0.89
    inent
    0.88
    Act Density 0.047%

    No Known Activations