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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "But" followed by contrasting information

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "But" at the beginning of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    States
    -0.68
    etermin
    -0.67
    dayName
    -0.66
    keyes
    -0.65
    arest
    -0.65
    Optional
    -0.63
     Assist
    -0.62
    Recommend
    -0.62
    CI
    -0.62
     Suggest
    -0.61
    POSITIVE LOGITS
     alas
    1.50
    tons
    1.06
     luckily
    1.04
     tragically
    1.01
     unfortunately
    1.01
     sadly
    1.01
     lately
    1.00
     fortunately
    0.98
     thankfully
    0.96
     unlike
    0.94
    Act Density 0.221%

    No Known Activations