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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to updates and changes in software or application features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arious
    -0.73
    fail
    -0.61
    SHIP
    -0.60
     Cyn
    -0.60
     helpless
    -0.59
    Ask
    -0.58
    ielding
    -0.57
    bound
    -0.57
    ournals
    -0.57
    dom
    -0.57
    POSITIVE LOGITS
     redesigned
    1.68
     revamped
    1.61
     improvements
    1.60
     improved
    1.59
     enhancements
    1.58
     redesign
    1.57
     overhaul
    1.57
     tweaks
    1.48
     additions
    1.39
     revised
    1.39
    Act Density 0.916%

    No Known Activations