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

    Neuronpedia

    INDEX
    Explanations

    types and categories of examples in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urre
    -0.17
    uddle
    -0.17
    аза
    -0.16
     allen
    -0.16
    Scope
    -0.16
    ",__
    -0.14
    bsolute
    -0.14
     Rica
    -0.14
    oenix
    -0.14
    razier
    -0.14
    POSITIVE LOGITS
    iating
    0.16
     Millenn
    0.16
    оÑĢов
    0.15
    depending
    0.15
    etypes
    0.15
     Helm
    0.14
    ALI
    0.14
    opus
    0.14
    iators
    0.14
    iator
    0.14
    Act Density 0.159%

    No Known Activations