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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categories and classifications of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Types
    -0.44
     Typen
    -0.44
    Types
    -0.39
     telle
    -0.37
     TYPES
    -0.36
    Typical
    -0.36
     типи
    -0.36
     telles
    -0.35
     subtypes
    -0.33
     khas
    -0.32
    POSITIVE LOGITS
     kind
    1.95
    kind
    1.52
     sort
    1.41
     KIND
    1.31
     Kind
    1.27
    Kind
    1.25
    KIND
    1.19
     kinda
    1.17
    sort
    1.07
     sorta
    1.07
    Act Density 0.223%

    No Known Activations