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

    Neuronpedia

    INDEX
    Explanations

    visually related terms specifically related to the eye

    oai_token-act-pair · gpt-3.5-turbo

    references to "eye" and its various contexts or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.67
     Resistance
    -0.66
    lishes
    -0.65
     Violent
    -0.65
     Vide
    -0.65
     Narr
    -0.64
    minus
    -0.64
     Duchess
    -0.63
    _-
    -0.62
    itative
    -0.62
    POSITIVE LOGITS
     sockets
    1.08
     eye
    1.07
    eyed
    0.99
    eye
    0.92
     eyebrow
    0.90
     lobe
    0.89
    bone
    0.84
    phal
    0.83
    bones
    0.82
     gou
    0.81
    Act Density 0.012%

    No Known Activations