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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to eye movements and expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to eyes and their expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adium
    -0.76
    ggies
    -0.68
    channelAvailability
    -0.63
    ALLY
    -0.62
    cific
    -0.61
    xual
    -0.61
    _-
    -0.60
    TON
    -0.60
    vich
    -0.60
    MER
    -0.59
    POSITIVE LOGITS
    ight
    1.18
     sockets
    1.13
    pots
    0.98
    abre
    0.82
    eyed
    0.81
     bulb
    0.81
     gaze
    0.80
    erver
    0.79
    ystem
    0.79
     gou
    0.79
    Act Density 0.017%

    No Known Activations