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

    Neuronpedia

    INDEX
    Explanations

    references to constants and their definitions in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordin
    -0.18
    aso
    -0.17
    faq
    -0.17
    hl
    -0.16
    atics
    -0.16
    ãĥĩãĥ«
    -0.16
    atically
    -0.15
    age
    -0.15
    hos
    -0.15
    erson
    -0.15
    POSITIVE LOGITS
    uctor
    0.20
    aneously
    0.19
    ellation
    0.18
    igham
    0.18
    inois
    0.18
    ine
    0.17
    inea
    0.16
    aneous
    0.16
    yne
    0.16
    .Constant
    0.15
    Act Density 0.023%

    No Known Activations