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

    Neuronpedia

    INDEX
    Explanations

    information about places to stay or accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lounge
    -0.16
    jde
    -0.15
    .Orientation
    -0.14
     seated
    -0.14
    aine
    -0.14
    emey
    -0.14
    baz
    -0.14
     carried
    -0.14
    rawer
    -0.14
    .launch
    -0.13
    POSITIVE LOGITS
     hotel
    0.27
     accommodation
    0.26
     bed
    0.26
     hotels
    0.25
     beds
    0.24
     sleeping
    0.24
     Hotel
    0.23
     motel
    0.23
     accommodations
    0.21
     dorm
    0.21
    Act Density 0.212%

    No Known Activations