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

    Neuronpedia

    INDEX
    Explanations

    complex or contrasting ideas or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" indicating contrast or complication in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roy
    -0.75
    morning
    -0.75
    itto
    -0.70
    million
    -0.70
    rush
    -0.67
    amus
    -0.67
    Times
    -0.67
    vance
    -0.67
    inence
    -0.66
    oire
    -0.65
    POSITIVE LOGITS
     nevertheless
    1.10
     alas
    1.09
     nonetheless
    1.09
    tons
    1.02
     fortunately
    0.91
     unfortunately
    0.84
     luckily
    0.82
    chery
    0.81
     hey
    0.81
     thankfully
    0.77
    Act Density 0.181%

    No Known Activations