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

    Neuronpedia

    INDEX
    Explanations

    references to the ability to see or perceive things visually

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of visibility or seeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.71
    inion
    -0.70
    adding
    -0.65
     notor
    -0.64
     incentiv
    -0.64
    orst
    -0.63
    emetery
    -0.62
    ItemImage
    -0.62
    requisite
    -0.61
     Tactics
    -0.61
    POSITIVE LOGITS
    ocular
    0.95
    lights
    0.91
    seeing
    0.88
     afar
    0.86
    dust
    0.82
    finder
    0.82
    ight
    0.81
     daylight
    0.81
    ibility
    0.79
    ById
    0.76
    Act Density 0.133%

    No Known Activations