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

    Neuronpedia

    INDEX
    Explanations

    descriptions of mathematical properties and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hani
    -0.15
    pert
    -0.15
    landa
    -0.14
    è£ķ
    -0.14
    лиÑĪком
    -0.14
    "group
    -0.14
     ÐĶаÑĤа
    -0.14
     ----------------------------------------------------------------------------↵
    -0.13
    [section
    -0.13
     Choice
    -0.13
    POSITIVE LOGITS
     exactly
    0.17
     size
    0.16
     respect
    0.15
    ittings
    0.15
    iture
    0.15
    λεÏį
    0.15
     prescribed
    0.14
    Embedded
    0.14
    usted
    0.14
     name
    0.14
    Act Density 0.125%

    No Known Activations