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

    Neuronpedia

    INDEX
    Explanations

    image captions within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to image captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apeshifter
    -0.80
     challeng
    -0.80
    etheless
    -0.77
    magic
    -0.77
     desper
    -0.75
    nova
    -0.75
     lull
    -0.75
    inki
    -0.74
    ĪĴ
    -0.73
     endeavor
    -0.72
    POSITIVE LOGITS
     Protesters
    1.26
     Thousands
    1.23
     Residents
    1.07
     Scenes
    1.07
     Hundreds
    1.06
     Officials
    1.05
     Researchers
    1.05
     Tens
    1.04
     Some
    1.03
     Students
    1.02
    Act Density 0.010%

    No Known Activations