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

    Neuronpedia

    INDEX
    Explanations

    references to size and scaling in various contexts

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

    the word "size"

    np_acts-logits-general · gemini-2.0-flash

    size measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.78
    abstractmethod
    -0.65
     NSCoder
    -0.64
    })));
    -0.63
    /</
    -0.62
    Penta
    -0.60
     '@/
    -0.59
    }(),
    -0.59
    opard
    -0.58
    Portale
    -0.57
    POSITIVE LOGITS
     SIZE
    1.38
     size
    1.30
     Size
    1.23
     sizes
    1.21
     Siz
    1.17
    SIZE
    1.16
     sizing
    1.11
    size
    1.09
     sized
    1.08
    Size
    1.08
    Act Density 0.152%

    No Known Activations