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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical actions in a noisy or chaotic context

    oai_token-act-pair · gpt-3.5-turbo

    references to video footage or recordings of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fortnight
    -0.70
     winters
    -0.67
    ships
    -0.66
    issance
    -0.66
    ventions
    -0.66
     minded
    -0.65
    rats
    -0.64
     preferring
    -0.63
    aea
    -0.62
     relativity
    -0.61
    POSITIVE LOGITS
     footage
    1.30
     narrator
    1.14
     clips
    1.07
     caption
    1.05
     camer
    1.03
     VIDEO
    1.02
     clip
    1.01
     filmed
    1.00
     bystanders
    1.00
     yells
    0.97
    Act Density 0.430%

    No Known Activations