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

    Neuronpedia

    INDEX
    Explanations

    comments or dialogue in text

    oai_token-act-pair · gpt-3.5-turbo

    indicators of document structure or formatting, possibly identifying distinct sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspected
    -0.78
     nationally
    -0.76
     national
    -0.73
     nationwide
    -0.72
     birthplace
    -0.71
     televised
    -0.71
     waged
    -0.70
     alleged
    -0.69
     imprisoned
    -0.69
     embattled
    -0.68
    POSITIVE LOGITS
    edit
    1.10
    Anyway
    1.09
    Quote
    1.09
    Installation
    1.06
    Reviewer
    1.02
    Secondly
    1.01
    Basically
    0.97
    Spoiler
    0.95
    */
    0.94
    prototype
    0.94
    Act Density 0.647%

    No Known Activations