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

    Neuronpedia

    INDEX
    Explanations

    computer code or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    the token representing the end of text or a section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laureate
    -0.69
     celebr
    -0.68
     systematic
    -0.65
     heads
    -0.62
    ãĤ£
    -0.62
     Thumbnails
    -0.62
     galleries
    -0.62
     Polly
    -0.60
     diapers
    -0.60
    terday
    -0.59
    POSITIVE LOGITS
    orea
    1.25
    rieg
    1.18
    EEP
    1.17
    atherine
    1.16
    icking
    1.16
    eeper
    1.14
    udos
    1.13
    ratom
    1.11
    idding
    1.11
    ernel
    1.11
    Act Density 0.050%

    No Known Activations