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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "but" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.81
    usting
    -0.76
    iggurat
    -0.75
    sense
    -0.73
    dayName
    -0.67
    edu
    -0.66
    代
    -0.65
    oire
    -0.64
    Laughs
    -0.64
    ivot
    -0.63
    POSITIVE LOGITS
     declined
    1.02
     lacked
    0.97
     retains
    0.96
     alas
    0.95
     lacks
    0.94
     excludes
    0.91
     fortunately
    0.91
     nevertheless
    0.91
     luckily
    0.90
     unlike
    0.88
    Act Density 0.166%

    No Known Activations