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

    Neuronpedia

    INDEX
    Explanations

    dimensions specified with an 'x'

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations of dimensions or resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.88
    assetsadobe
    -0.80
    awaru
    -0.75
    utical
    -0.75
    ogy
    -0.75
    kson
    -0.74
     skelet
    -0.68
     Seym
    -0.68
    rent
    -0.68
     stru
    -0.68
    POSITIVE LOGITS
    LP
    0.81
    wid
    0.78
    IU
    0.77
    avier
    0.75
    Liquid
    0.74
    Glass
    0.72
    USB
    0.70
    LAB
    0.70
    Mas
    0.69
    Large
    0.69
    Act Density 0.024%

    No Known Activations