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

    Neuronpedia

    INDEX
    Explanations

    links prompting readers to "Read more" in an article or story

    oai_token-act-pair · gpt-3.5-turbo

    instances of commands or prompts to read

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aura
    -0.70
     territory
    -0.66
     outfit
    -0.65
     hall
    -0.65
     monopoly
    -0.63
    olina
    -0.63
     opponent
    -0.63
     minion
    -0.63
     cape
    -0.62
     machine
    -0.61
    POSITIVE LOGITS
    Read
    3.71
     Read
    2.11
    READ
    2.06
    read
    1.94
    Write
    1.89
    reads
    1.68
    Reading
    1.59
     read
    1.48
     READ
    1.47
    MORE
    1.44
    Act Density 0.010%

    No Known Activations