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

    Neuronpedia

    INDEX
    Explanations

    locations within a building, specifically focusing on 'hall' and 'hallways'

    oai_token-act-pair · gpt-3.5-turbo

    references to "halls" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annotations
    -0.73
    EED
    -0.71
    uyomi
    -0.68
    ossibility
    -0.66
    olitics
    -0.66
     Copy
    -0.65
    vernment
    -0.63
    aminer
    -0.62
    odcast
    -0.61
     flakes
    -0.61
    POSITIVE LOGITS
    ways
    1.52
    owed
    1.28
    way
    1.25
    iday
    1.18
    marks
    1.18
    fare
    1.09
    WAY
    1.07
     hall
    1.06
    ows
    1.04
    ibur
    1.03
    Act Density 0.015%

    No Known Activations