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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific physical locations, particularly booths

    oai_token-act-pair · gpt-3.5-turbo

    references to booths or similar structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensions
    -0.69
    itals
    -0.69
    mitted
    -0.68
    ochond
    -0.67
    itars
    -0.63
     acron
    -0.62
    ract
    -0.61
    ension
    -0.60
    mitting
    -0.60
    nesses
    -0.59
    POSITIVE LOGITS
     booth
    1.08
     booths
    0.97
    holder
    0.95
    holders
    0.92
    cloth
    0.87
    washer
    0.85
    swer
    0.80
    handler
    0.79
    wagon
    0.78
     exhib
    0.76
    Act Density 0.013%

    No Known Activations