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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations within a building, specifically focusing on "halls"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hall" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Him
    -0.68
     Annotations
    -0.67
     Copy
    -0.66
     Leilan
    -0.65
    uyomi
    -0.63
    EED
    -0.62
     Save
    -0.62
    itars
    -0.61
     Typhoon
    -0.61
    ossibility
    -0.60
    POSITIVE LOGITS
    ways
    1.41
    owed
    1.27
    marks
    1.25
    iday
    1.18
    way
    1.17
     hall
    1.08
    WAY
    1.07
    ibur
    1.06
    ows
    1.03
    fare
    0.95
    Act Density 0.010%

    No Known Activations