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

    Neuronpedia

    INDEX
    Explanations

    news article structures such as headlines, with a focus on video content

    oai_token-act-pair · gpt-3.5-turbo

    sections related to video content or multimedia features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertation
    -0.70
    beit
    -0.67
     lashes
    -0.64
    endix
    -0.63
    eca
    -0.61
    printf
    -0.60
    helm
    -0.60
    arag
    -0.60
     strat
    -0.60
     indent
    -0.59
    POSITIVE LOGITS
    Sports
    0.71
    Trend
    0.70
     Trend
    0.68
    Pict
    0.68
    Sport
    0.66
     Que
    0.66
     Kiw
    0.66
     Pict
    0.65
     Gorge
    0.63
     Replay
    0.63
    Act Density 0.038%

    No Known Activations