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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing contrasts or contradictions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vance
    -0.73
    nan
    -0.72
    rontal
    -0.69
    olid
    -0.68
    flush
    -0.67
    rys
    -0.67
    register
    -0.67
    lish
    -0.67
    ribed
    -0.66
    etts
    -0.66
    POSITIVE LOGITS
     alas
    1.00
     beware
    0.99
     downside
    0.94
     unfortunately
    0.91
     hindered
    0.85
     lacks
    0.84
     drawbacks
    0.80
     drawback
    0.77
     hampered
    0.77
     lacked
    0.76
    Act Density 0.428%

    No Known Activations