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

    Neuronpedia

    INDEX
    Explanations

    configurations and settings

    oai_token-act-pair · gpt-3.5-turbo

    references to configuration files and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.86
     Apost
    -0.78
    FORE
    -0.78
     Gael
    -0.74
     bye
    -0.72
     Jagu
    -0.72
    Downloadha
    -0.71
     polio
    -0.69
     Karen
    -0.69
     Antiqu
    -0.65
    POSITIVE LOGITS
    uration
    1.75
    urations
    1.60
    urable
    1.39
    urated
    1.22
    ured
    1.19
    uring
    1.11
    urer
    1.10
    ure
    1.05
    urers
    0.99
    config
    0.98
    Act Density 0.016%

    No Known Activations