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

    Neuronpedia

    INDEX
    Explanations

    adverbs that express a significant degree of change or impact

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating significant changes or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifully
    -0.83
    afety
    -0.80
    elsen
    -0.78
    aple
    -0.76
    icip
    -0.75
    aleb
    -0.74
    sburgh
    -0.73
    tein
    -0.70
    inently
    -0.69
    tale
    -0.67
    POSITIVE LOGITS
     reduced
    0.98
     impacted
    0.97
     reduce
    0.96
     reduces
    0.95
     impacting
    0.94
     altered
    0.92
     underest
    0.91
     outwe
    0.91
     differ
    0.90
     outnumbered
    0.90
    Act Density 0.065%

    No Known Activations