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

    Neuronpedia

    INDEX
    Explanations

    references to eyewear and vision-related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamo
    -0.15
    à¹Ģà¸ŀล
    -0.15
    elop
    -0.14
    nr
    -0.14
    609
    -0.14
    hec
    -0.14
    ipple
    -0.14
    urre
    -0.13
    796
    -0.13
     dyn
    -0.13
    POSITIVE LOGITS
     lenses
    0.47
     lens
    0.39
     glasses
    0.38
     Lens
    0.37
    Lens
    0.35
     Glasses
    0.33
     sunglasses
    0.33
     ey
    0.31
     prescription
    0.29
     frames
    0.28
    Act Density 0.019%

    No Known Activations