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

    Neuronpedia

    INDEX
    Explanations

    coding-related terms and syntax symbols, especially involving variables and assignments

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the "@" symbol, potentially indicating email addresses, handles, or tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.81
     reconc
    -0.73
     pneum
    -0.71
     defic
    -0.70
     Malk
    -0.64
    éĹĺ
    -0.62
     orche
    -0.62
    uyomi
    -0.61
     circulation
    -0.61
     Scandinavian
    -0.61
    POSITIVE LOGITS
    #$
    1.34
    @@@@@@@@
    1.01
    gmail
    0.87
    LINE
    0.86
    realDonaldTrump
    0.83
    home
    0.82
    BY
    0.79
    mid
    0.75
    Home
    0.75
    taboola
    0.75
    Act Density 0.016%

    No Known Activations