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

    Neuronpedia

    INDEX
    Explanations

    words related to vision or visual perception

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "vision" and its variations, indicating a focus on topics related to visual perception or visual media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pept
    -0.72
     fir
    -0.70
     unloaded
    -0.69
     hom
    -0.67
     pump
    -0.65
     ammon
    -0.63
     CTR
    -0.62
     intercepted
    -0.61
     discharged
    -0.60
     heap
    -0.59
    POSITIVE LOGITS
    vision
    4.65
    Vision
    2.52
     Vision
    1.85
     vision
    1.51
    vised
    1.32
    sight
    1.21
    visor
    1.18
    voy
    1.17
    VIS
    1.14
    visors
    1.05
    Act Density 0.011%

    No Known Activations