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

    Neuronpedia

    INDEX
    Explanations

    references to hotels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.71
    ||}
    -0.69
     Avez
    -0.65
    WebVitals
    -0.64
     barbacoa
    -0.64
    Personensuche
    -0.63
    paksa
    -0.63
    digm
    -0.63
     nhau
    -0.63
    givers
    -0.62
    POSITIVE LOGITS
     hotel
    2.11
     hotels
    2.08
     Hotel
    1.99
     Hotels
    1.93
     HOTEL
    1.92
    hotel
    1.92
    Hotels
    1.85
    HOTEL
    1.77
    Hotel
    1.77
    hotels
    1.65
    Act Density 0.024%

    No Known Activations