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

    Neuronpedia

    INDEX
    Explanations

    specific types of formatted citations, potentially related to academia or research work

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thrott
    -0.75
     lucky
    -0.73
     coughing
    -0.71
     stomp
    -0.69
     consuming
    -0.68
     destro
    -0.67
    angled
    -0.66
     spitting
    -0.66
     girlfriends
    -0.66
     radius
    -0.65
    POSITIVE LOGITS
    âĵĺ
    1.03
    BOOK
    0.92
    phasis
    0.91
    TABLE
    0.90
    References
    0.88
    sites
    0.86
    Review
    0.84
    âĨ
    0.83
     PubMed
    0.82
    International
    0.82
    Act Density 0.217%

    No Known Activations