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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate notoriety or recognition of people, places, or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "known for" followed by descriptive attributes or characteristics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.64
     surla
    -0.64
    GenerationType
    -0.55
     Reſ
    -0.55
     Diſ
    -0.54
     Perſ
    -0.54
     Eſ
    -0.53
    ylvan
    -0.52
    ########.
    -0.52
     RISERVATA
    -0.51
    POSITIVE LOGITS
    Known
    0.53
     known
    0.52
     reputation
    0.51
     Known
    0.50
    known
    0.46
     throughout
    0.46
     famous
    0.45
     notoriously
    0.44
     fame
    0.43
     dikenal
    0.43
    Act Density 0.119%

    No Known Activations