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

    Neuronpedia

    INDEX
    Explanations

    news agencies related to images and captions

    oai_token-act-pair · gpt-3.5-turbo

    references to news agencies and image copyrights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SHALL
    -0.83
    Reviewer
    -0.72
    represented
    -0.68
     advis
    -0.67
     sworn
    -0.65
     includ
    -0.65
    relevant
    -0.64
    iqueness
    -0.63
     reconc
    -0.63
     undermin
    -0.63
    POSITIVE LOGITS
     Image
    1.35
     Images
    1.10
     IMAGES
    1.08
    Images
    0.87
    Image
    0.84
     Photos
    0.84
     /
    0.81
     image
    0.81
     images
    0.79
     caption
    0.78
    Act Density 0.030%

    No Known Activations