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

    Neuronpedia

    INDEX
    Explanations

    programming related terms in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swell
    -0.79
     underestimated
    -0.76
     leaving
    -0.76
     knowing
    -0.74
     awhile
    -0.74
     multiplying
    -0.72
     displ
    -0.71
     fatig
    -0.70
     overlooked
    -0.70
     exhausting
    -0.70
    POSITIVE LOGITS
    plugins
    1.28
    common
    1.27
    enabled
    1.21
    services
    1.14
    general
    1.14
    plugin
    1.14
    dll
    1.14
    simple
    1.13
    internal
    1.12
    policy
    1.11
    Act Density 0.062%

    No Known Activations