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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "seeing" or its variations, indicating a focus on visual perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.46
     ujednoznacz
    -0.44
    localctx
    -0.43
    Дорогие
    -0.40
    ofis
    -0.40
     loose
    -0.38
    Rè
    -0.37
    */].
    -0.36
    olism
    -0.36
    routeProvider
    -0.36
    POSITIVE LOGITS
     seeing
    3.02
     Seeing
    2.67
    seeing
    2.64
    Seeing
    2.58
     saw
    2.19
     seen
    2.05
    saw
    1.91
     sees
    1.90
    seen
    1.88
     melihat
    1.88
    Act Density 0.212%

    No Known Activations