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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hesitation or conflict

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roy
    -0.71
    ampa
    -0.69
    ump
    -0.69
    tnc
    -0.65
    entry
    -0.65
    agra
    -0.64
    venue
    -0.64
    aband
    -0.63
     segment
    -0.62
    built
    -0.61
    POSITIVE LOGITS
    tons
    1.19
     alas
    1.09
     nevertheless
    0.96
     luckily
    0.94
    chery
    0.93
     hey
    0.93
     fortunately
    0.88
     nonetheless
    0.87
     THEN
    0.76
     unfortunately
    0.76
    Act Density 0.233%

    No Known Activations