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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rigs
    -0.64
     drawer
    -0.62
     spont
    -0.61
     peg
    -0.60
     gag
    -0.58
     wells
    -0.58
    ussy
    -0.57
     upfront
    -0.56
     sticks
    -0.56
     booths
    -0.56
    POSITIVE LOGITS
    actionDate
    0.94
     ][
    0.70
    channelAvailability
    0.70
    ::::::::
    0.69
    pmwiki
    0.69
    ,,,,,,,,
    0.68
    align
    0.68
    ojure
    0.68
    then
    0.67
     Accessed
    0.66
    Act Density 0.056%

    No Known Activations