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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that introduce lists, examples, or elaborations, often followed by commas.

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

    references to numerical sports scores and results.

    oai_token-act-pair · gemini-1.5-proTriggered by @jbloomaus

    text related to sports accomplishments and statistics.

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

    financial terms and concepts

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

    frequently following commas

    np_acts-logits-general · gemini-2.0-flash

    verbs ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.64
     tắc
    -0.62
    lexikon
    -0.57
     mọi
    -0.54
    úb
    -0.52
     Depends
    -0.52
    ullo
    -0.52
    Eksterne
    -0.51
    ordo
    -0.51
    ̀nh
    -0.50
    POSITIVE LOGITS
     making
    1.22
     giving
    1.21
     becoming
    1.15
     offering
    1.12
     providing
    1.11
     bringing
    1.09
     allowing
    1.08
     having
    1.07
     ensuring
    1.06
     taking
    1.05
    Act Density 0.461%

    No Known Activations