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

    Neuronpedia

    INDEX
    Explanations

    references to size and measurements, particularly in a comparative or evaluative context

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

    words and phrases related to size, quantity, and scale (particularly when describing growth, expansion, or comparisons of magnitude).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.45
    verbatim
    -0.33
    scrollLeft
    -0.32
    onius
    -0.32
    rungsseite
    -0.31
    Masked
    -0.30
    atshirt
    -0.30
    ruik
    -0.28
    dengar
    -0.28
    ówki
    -0.28
    POSITIVE LOGITS
     larger
    2.33
     size
    2.19
     Larger
    2.16
    Larger
    2.14
    larger
    2.14
     bigger
    2.13
     smaller
    1.99
     sizes
    1.98
     large
    1.95
     sized
    1.94
    Act Density 1.634%

    No Known Activations