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

    Neuronpedia

    INDEX
    Explanations

    instances of humor, specifically the use of "lol" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.54
     el
    -0.50
      
    -0.49
    .
    -0.48
    el
    -0.47
     One
    -0.46
     one
    -0.45
    permum
    -0.45
    чук
    -0.45
     El
    -0.44
    POSITIVE LOGITS
     للمعارف
    1.03
     للاسماء
    1.00
    ]--;
    0.99
     ujednoznacz
    0.94
     LOL
    0.92
     Lol
    0.91
     lol
    0.90
    InputTagHelper
    0.87
     Allociné
    0.87
     calendriers
    0.87
    Act Density 0.019%

    No Known Activations