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

    Neuronpedia

    INDEX
    Explanations

    descriptions of sightings, particularly related to large objects or events

    oai_token-act-pair · gpt-3.5-turbo

    large objects and associated measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.81
    OUP
    -0.72
    aund
    -0.69
     poisons
    -0.68
    imester
    -0.67
    cest
    -0.67
     boycot
    -0.66
     detox
    -0.66
     marriages
    -0.66
    udeb
    -0.65
    POSITIVE LOGITS
     hovering
    1.36
     silhou
    1.36
     silhouette
    1.28
     UFOs
    1.14
     sighting
    1.12
     circled
    1.10
     horizon
    1.09
     circling
    1.09
     illuminated
    1.08
     overhead
    1.08
    Act Density 0.371%

    No Known Activations