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

    Neuronpedia

    INDEX
    Explanations

    image captions

    oai_token-act-pair · gpt-3.5-turbo

    instances of image captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.83
    apeshifter
    -0.79
    inki
    -0.71
    icum
    -0.70
    linger
    -0.69
    nuts
    -0.67
     lull
    -0.67
     bulb
    -0.67
    walker
    -0.67
    nova
    -0.67
    POSITIVE LOGITS
     Thousands
    1.08
     Protesters
    1.06
     Aerial
    0.87
     IMAGES
    0.87
     Previous
    0.86
     Scenes
    0.85
     Researchers
    0.85
     Hundreds
    0.84
     Highlights
    0.84
     Earlier
    0.83
    Act Density 0.009%

    No Known Activations