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

    Neuronpedia

    INDEX
    Explanations

    dates in the month/day format

    oai_token-act-pair · gpt-3.5-turbo

    dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.66
     screwed
    -0.65
     suite
    -0.62
    wered
    -0.62
     Ital
    -0.61
    ortium
    -0.59
     VIDEOS
    -0.58
    initely
    -0.58
    letes
    -0.58
    ilib
    -0.57
    POSITIVE LOGITS
    eteenth
    1.02
     occasions
    0.96
     eve
    0.95
    flower
    0.80
     occasion
    0.75
     heels
    0.74
     1886
    0.73
    imeo
    0.72
    âĸĪâĸĪ
    0.71
     weekends
    0.71
    Act Density 0.055%

    No Known Activations