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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals in different contexts, such as players, family members, or public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups involved in competitive or performance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.86
     Continued
    -0.77
    ItemTracker
    -0.69
    EngineDebug
    -0.67
    MpServer
    -0.65
    thens
    -0.65
    protected
    -0.64
    ca
    -0.64
    OULD
    -0.62
    didn
    -0.62
    POSITIVE LOGITS
     perform
    1.29
     emerge
    1.28
     lose
    1.23
     stumble
    1.22
     explode
    1.22
     disappear
    1.22
     develop
    1.21
     crumble
    1.21
     succeed
    1.21
     evolve
    1.20
    Act Density 0.214%

    No Known Activations