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

    Neuronpedia

    INDEX
    Explanations

    dates or numbers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers or signify the conclusion of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.72
     streng
    -0.68
     cryst
    -0.64
    ILY
    -0.62
     Rite
    -0.62
    Versions
    -0.62
     blat
    -0.60
     predec
    -0.60
     Figures
    -0.59
     melts
    -0.59
    POSITIVE LOGITS
    heed
    0.96
    atre
    0.94
    chen
    0.91
    backer
    0.89
    fters
    0.84
    glass
    0.78
    ãĤ¦ãĤ¹
    0.78
    neys
    0.78
    berra
    0.77
    amiya
    0.77
    Act Density 0.100%

    No Known Activations