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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "all" or totality across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fty
    -0.15
    keh
    -0.15
     Exceptions
    -0.15
    imers
    -0.14
    ãģ¡ãģ¯
    -0.14
     particular
    -0.14
    eprom
    -0.14
     trÃŃ
    -0.14
    HasBeenSet
    -0.14
    andbox
    -0.14
    POSITIVE LOGITS
     sorts
    0.44
     kinds
    0.42
     manner
    0.33
     types
    0.32
    sort
    0.30
     sort
    0.29
     KIND
    0.29
     kind
    0.29
     SORT
    0.27
     aspects
    0.26
    Act Density 0.083%

    No Known Activations