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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Rel" followed by a number indicating its level of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "real" or "related" entities, predominantly in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.95
    enegger
    -0.69
    avorite
    -0.67
    BOX
    -0.66
    thur
    -0.65
    schild
    -0.65
    manship
    -0.63
    terday
    -0.63
    gerald
    -0.63
    ãģ®ç
    -0.63
    POSITIVE LOGITS
    igion
    1.26
    iance
    1.24
    iever
    1.21
    iability
    1.18
    iable
    1.10
    atively
    1.05
    inqu
    1.01
    ieved
    1.00
    ievers
    1.00
    ativity
    1.00
    Act Density 0.013%

    No Known Activations