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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media and personal interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to communication events and interactions with specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢij
    -0.91
    ©¶æ¥µ
    -0.83
    ,—
    -0.78
    ¶
    -0.74
    —
    -0.71
    Newsletter
    -0.71
    —"
    -0.68
    Footnote
    -0.68
    Abstract
    -0.64
     Index
    -0.64
    POSITIVE LOGITS
     @
    1.25
    sic
    1.12
     pics
    1.03
     congr
    1.03
     #
    0.99
    DonaldTrump
    0.96
    ????????
    0.95
     ðŁ
    0.95
    ðŁĺ
    0.94
    ï¸ı
    0.93
    Act Density 0.512%

    No Known Activations