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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "all" and related expressions indicating totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     device
    -0.52
     programme
    -0.51
     Jacobsen
    -0.47
     scheme
    -0.47
     Jacobson
    -0.45
     febru
    -0.43
     Hodgson
    -0.43
     DEVICE
    -0.43
     object
    -0.42
     Schröder
    -0.42
    POSITIVE LOGITS
     All
    1.34
    All
    1.31
     all
    1.27
     ALL
    1.11
    setAll
    1.05
    all
    1.05
     Semua
    1.02
    ALL
    1.01
     semua
    0.92
    ReadAll
    0.86
    Act Density 0.238%

    No Known Activations