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

    Neuronpedia

    INDEX
    Explanations

    specific references or citations in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to citations or legal references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alth
    -0.75
     Dim
    -0.73
    creen
    -0.70
    aky
    -0.70
    opian
    -0.69
     chats
    -0.69
    eks
    -0.67
    Kit
    -0.67
     fren
    -0.65
    aiden
    -0.65
    POSITIVE LOGITS
     citation
    4.36
     citations
    3.27
     Citation
    3.03
     cite
    1.80
     attribution
    1.65
     quotation
    1.41
     quotations
    1.40
     cited
    1.29
     Attribution
    1.20
     citing
    1.17
    Act Density 0.030%

    No Known Activations