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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases that indicate positive recognition or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flesh
    -0.19
    auer
    -0.18
    ansson
    -0.17
     Herrera
    -0.17
    asant
    -0.17
    sville
    -0.16
    EMPLARY
    -0.14
    dana
    -0.14
    odon
    -0.14
    ->__
    -0.14
    POSITIVE LOGITS
    ceipt
    0.14
    aways
    0.14
    LayoutConstraint
    0.14
    Ú¯ÛĮ
    0.14
    aved
    0.13
    INGS
    0.13
     Lords
    0.13
    ÑĦÑĸ
    0.13
     re
    0.13
    /wp
    0.13
    Act Density 0.167%

    No Known Activations