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

    Neuronpedia

    INDEX
    Explanations

    mentions of hotels

    oai_token-act-pair · gpt-3.5-turbo

    references to hotels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.82
     Anarchy
    -0.78
    İĭ
    -0.73
     advers
    -0.70
    nces
    -0.68
    nir
    -0.68
    umbnail
    -0.67
     Izan
    -0.66
    cale
    -0.66
     Prompt
    -0.65
    POSITIVE LOGITS
     rooms
    1.03
     accommodations
    0.98
     hotel
    0.93
     guests
    0.89
     room
    0.88
     hotels
    0.88
     accommodation
    0.87
     Hotel
    0.87
    room
    0.82
     occupancy
    0.82
    Act Density 0.029%

    No Known Activations