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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terms related to linear algebra.

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

    mathematical equations and terms.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mathematical notation involving superscript -1, typically indicating inverse operations or functions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Superscripted inverse symbols

    np_acts-logits-general · gemini-2.0-flash

    inverse of 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    -0.71
    NewRow
    -0.66
    řen
    -0.56
    LOYEES
    -0.56
     kasarigan
    -0.56
    Obrázky
    -0.54
     đu
    -0.54
    raborty
    -0.53
    eniu
    -0.52
    hime
    -0.52
    POSITIVE LOGITS
    Transkript
    0.71
     Bish
    0.66
    AnimationFrame
    0.63
     nakalista
    0.63
     Temmuz
    0.62
    äsenti
    0.61
     Wand
    0.59
    śmy
    0.59
     "'");
    0.58
     voglia
    0.57
    Act Density 0.250%

    No Known Activations