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

    Neuronpedia

    INDEX
    Explanations

    exclamations and emotionally charged language

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal identity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.98
    actionDate
    -0.75
     )]
    -0.73
     largeDownload
    -0.71
     principally
    -0.69
     unrem
    -0.68
    )].
    -0.67
     rhet
    -0.62
     footnote
    -0.61
     pragmatic
    -0.60
    POSITIVE LOGITS
    !
    2.19
    !!
    2.14
    !!!
    2.03
    !!!!
    1.91
    ?!
    1.81
    !!!!!
    1.80
    !?
    1.80
    !'
    1.74
    !.
    1.73
    !:
    1.72
    Act Density 0.508%

    No Known Activations