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

    Neuronpedia

    INDEX
    Explanations

    words related to vision or the act of seeing in a literal or metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to vision and perceiving the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stead
    -0.72
    inion
    -0.70
     suscept
    -0.68
    EStreamFrame
    -0.67
    adding
    -0.66
     reign
    -0.64
    idity
    -0.60
     moratorium
    -0.60
    prep
    -0.60
    bia
    -0.59
    POSITIVE LOGITS
     fit
    1.07
    dust
    1.05
     visions
    0.98
     eye
    0.98
     firsthand
    0.85
     daylight
    0.84
    eye
    0.83
     pictures
    0.82
     through
    0.81
     Eye
    0.80
    Act Density 0.085%

    No Known Activations