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

    Neuronpedia

    INDEX
    Explanations

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

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

    "all" followed by nouns describing types or kinds

    np_acts-logits-general · gemini-2.0-flash

    all sorts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.66
    AccessorTable
    -0.66
     edelstahl
    -0.61
     houſe
    -0.58
     useAppContext
    -0.58
     leſs
    -0.58
     ImageIcon
    -0.55
     suivante
    -0.55
    MockBean
    -0.54
    IndentedString
    -0.53
    POSITIVE LOGITS
     sorts
    1.02
     manner
    1.00
     kinds
    0.88
    manner
    0.71
     sides
    0.67
     sortes
    0.67
    kinds
    0.63
     walks
    0.63
    aarrggbb
    0.61
     corners
    0.58
    Act Density 0.080%

    No Known Activations