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

    Neuronpedia

    INDEX
    Explanations

    editorial notes and comments within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of editorial notes or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.73
    ĪĴ
    -0.69
     ammon
    -0.67
    abouts
    -0.63
    illy
    -0.63
    omething
    -0.62
    urnal
    -0.61
     rhy
    -0.58
    akespe
    -0.57
     FML
    -0.57
    POSITIVE LOGITS
     Picks
    1.05
     Note
    0.78
    Publisher
    0.73
     note
    0.72
    lisher
    0.70
     drafts
    0.70
     Column
    0.69
    ש
    0.69
     Editor
    0.67
    lish
    0.66
    Act Density 0.075%

    No Known Activations