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

    Neuronpedia

    INDEX
    Explanations

    references to hotels and lodging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.78
    digm
    -0.66
    jus
    -0.64
     Cly
    -0.63
     Lippen
    -0.62
     getArguments
    -0.62
     Sra
    -0.61
     Rend
    -0.61
    -0.60
     caus
    -0.59
    POSITIVE LOGITS
     hotel
    2.52
     hotels
    2.43
     Hotel
    2.38
     Hotels
    2.27
     HOTEL
    2.26
    hotel
    2.25
    Hotel
    2.16
    Hotels
    2.13
    HOTEL
    2.03
    hotels
    1.94
    Act Density 0.050%

    No Known Activations