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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical actions involving movements, locations, and objects

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical impact or objects in motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AUD
    -0.70
    QL
    -0.70
    ONSORED
    -0.70
    PDATE
    -0.68
    Privacy
    -0.65
    Guest
    -0.64
    ãĤ¤ãĥĪ
    -0.64
    Specific
    -0.63
     proble
    -0.60
    Category
    -0.60
    POSITIVE LOGITS
     holes
    0.75
     mound
    0.73
     tiles
    0.72
     tray
    0.71
     protr
    0.71
     shaft
    0.68
     curved
    0.68
     hole
    0.68
     brim
    0.68
     horizontal
    0.67
    Act Density 0.660%

    No Known Activations