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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to hotel accommodations and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shop
    -0.16
     Barnes
    -0.15
    ounge
    -0.15
     picnic
    -0.15
    Seats
    -0.15
    Shop
    -0.15
     cafe
    -0.15
    shop
    -0.14
    Æ°á»
    -0.14
    ount
    -0.14
    POSITIVE LOGITS
     bed
    0.23
    otel
    0.22
     hotel
    0.20
     Hotel
    0.18
     beds
    0.18
    hotel
    0.17
    -bed
    0.17
     stay
    0.17
    alink
    0.17
    stay
    0.17
    Act Density 0.393%

    No Known Activations