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

    Neuronpedia

    INDEX
    Explanations

    identifiers and classifications within a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhe
    -0.14
     sofas
    -0.13
    OLUMN
    -0.13
    ipur
    -0.13
     ÑĤел
    -0.12
     Markus
    -0.12
    TECTION
    -0.12
     ì¶ľìŀ¥
    -0.12
     baskets
    -0.12
    illas
    -0.12
    POSITIVE LOGITS
     badge
    0.40
     pins
    0.40
     pin
    0.39
     badges
    0.39
     lap
    0.37
     Badge
    0.33
    badge
    0.33
     Pins
    0.33
     insign
    0.32
    -badge
    0.32
    Act Density 0.046%

    No Known Activations