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

    Neuronpedia

    INDEX
    Explanations

    visual content labels such as 'Photo' or related photography terms

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or images in a report

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushi
    -0.77
    anu
    -0.71
    uca
    -0.70
    apon
    -0.70
    etta
    -0.67
    itaire
    -0.67
    ichick
    -0.64
    utical
    -0.64
    qv
    -0.64
    aterasu
    -0.63
    POSITIVE LOGITS
    GREEN
    0.72
     ancest
    0.70
    PRESS
    0.68
    Loading
    0.68
    Press
    0.67
    ³³³³³³³³³³³³³³³³
    0.66
    Posted
    0.65
    WASHINGTON
    0.65
    WARNING
    0.65
    SAN
    0.64
    Act Density 0.441%

    No Known Activations