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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to social interactions and etiquette

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
    GenerationType
    -0.63
     tarihinde
    -0.62
     تانيه
    -0.62
    繋
    -0.53
     اون
    -0.53
    setupUi
    -0.50
    yntaxException
    -0.50
     optimizar
    -0.50
     meanwhile
    -0.49
    POSITIVE LOGITS
     indestru
    0.63
    qxd
    0.62
     [],
    0.62
    CHAPTER
    0.61
     entrée
    0.60
    chapter
    0.60
    Chapter
    0.57
    cotch
    0.55
    persky
    0.55
     CHAPTER
    0.54
    Act Density 0.783%

    No Known Activations