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

    Neuronpedia

    INDEX
    Explanations

    text related to configuring software settings or options

    oai_token-act-pair · gpt-3.5-turbo

    terms related to configurations and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.91
    Downloadha
    -0.79
     Laur
    -0.78
     Apost
    -0.77
     Karen
    -0.72
    bery
    -0.71
    birth
    -0.71
     Gael
    -0.70
    Hour
    -0.69
    âĹ¼
    -0.68
    POSITIVE LOGITS
    urable
    1.43
    urations
    1.36
    uration
    1.34
    urated
    1.20
    anooga
    1.06
     config
    1.02
     Config
    1.02
    Parser
    1.00
    config
    0.96
    uring
    0.96
    Act Density 0.005%

    No Known Activations