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

    Neuronpedia

    INDEX
    Explanations

    keywords related to eyes or vision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "eye" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.72
    theless
    -0.68
    _-
    -0.68
    channelAvailability
    -0.68
     Violent
    -0.65
    icum
    -0.65
     congr
    -0.64
    itative
    -0.63
    vik
    -0.62
    ities
    -0.61
    POSITIVE LOGITS
     sockets
    1.10
     socket
    0.89
     lobe
    0.86
    ight
    0.84
     eye
    0.83
    bones
    0.83
    beam
    0.80
     brow
    0.79
    socket
    0.76
    ewitness
    0.76
    Act Density 0.023%

    No Known Activations