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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks from the Twitter domain

    oai_token-act-pair · gpt-3.5-turbo

    references to the website Twitter.com

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.69
     candid
    -0.68
    oult
    -0.65
     burgl
    -0.65
     simple
    -0.65
     petty
    -0.62
     sanity
    -0.61
     thorn
    -0.61
     sober
    -0.60
    EStreamFrame
    -0.60
    POSITIVE LOGITS
    pleted
    0.88
    lishing
    0.87
    dp
    0.86
    pletion
    0.86
    com
    0.84
    verage
    0.82
    lisher
    0.80
    ournals
    0.79
    culosis
    0.79
     WATCHED
    0.78
    Act Density 0.031%

    No Known Activations