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

    Neuronpedia

    INDEX
    Explanations

    images or photographs

    oai_token-act-pair · gpt-3.5-turbo

    references to pictures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Introduced
    -0.71
    inion
    -0.71
    ressive
    -0.70
    upuncture
    -0.70
    cffff
    -0.70
    EED
    -0.70
     Archdemon
    -0.68
    osi
    -0.67
    margin
    -0.65
    ggles
    -0.65
    POSITIVE LOGITS
    ynthesis
    1.10
     pictures
    1.05
     pics
    1.00
    Pict
    0.98
    ynt
    0.96
    pict
    0.90
     galleries
    0.90
    picture
    0.87
     Pictures
    0.87
     Picture
    0.84
    Act Density 0.010%

    No Known Activations