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

    Neuronpedia

    INDEX
    Explanations

    terms related to classification categories, specifically "class" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "class" appearing in various contexts across different domains.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     noDo
    -0.59
     Paglinawan
    -0.59
    setVerticalGroup
    -0.57
     EconPapers
    -0.55
     հղումներ
    -0.54
     nawr
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    OGND
    -0.50
     <=",
    -0.50
     bandeira
    -0.50
    POSITIVE LOGITS
     Class
    0.67
    rooms
    0.65
     CLASS
    0.54
    ROOM
    0.54
    Class
    0.54
    ically
    0.50
     MyClass
    0.49
     Classe
    0.49
     Clas
    0.46
    forName
    0.45
    Act Density 0.150%

    No Known Activations