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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical locations or structures such as booths

    oai_token-act-pair · gpt-3.5-turbo

    references to booths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ren
    -0.71
    urs
    -0.65
    math
    -0.65
     Princ
    -0.64
    rase
    -0.63
    ict
    -0.61
    yt
    -0.61
    akespe
    -0.61
    ilda
    -0.61
    ort
    -0.59
    POSITIVE LOGITS
     booth
    4.25
     booths
    3.12
     Booth
    1.93
     kios
    1.36
     exhib
    1.28
     plaza
    1.08
     stall
    1.08
     aisle
    1.04
     stalls
    1.02
     billboard
    1.00
    Act Density 0.014%

    No Known Activations