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

    Neuronpedia

    INDEX
    Explanations

    references to luxury hotels and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugi
    -0.15
     Moy
    -0.15
    utsch
    -0.15
     reactive
    -0.14
     cục
    -0.14
    (strpos
    -0.14
    aliz
    -0.13
    élé
    -0.13
    alley
    -0.13
     stall
    -0.13
    POSITIVE LOGITS
     hotel
    0.55
     Hotel
    0.52
    hotel
    0.47
    Hotel
    0.45
     hotels
    0.42
     Hotels
    0.38
    ãĥĽãĥĨãĥ«
    0.36
    éħĴåºĹ
    0.35
     íĺ¸íħĶ
    0.34
     Resort
    0.33
    Act Density 0.098%

    No Known Activations