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

    Neuronpedia

    INDEX
    Explanations

    references to appendices or supplementary materials in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endwhile
    -0.45
     gql
    -0.41
     vernie
    -0.40
    isDebugEnabled
    -0.38
    netbeans
    -0.37
     reír
    -0.37
     ucapnya
    -0.37
    endaft
    -0.37
     /*#__
    -0.36
     présidenti
    -0.36
    POSITIVE LOGITS
     complement
    0.84
     appendix
    0.84
    Appendix
    0.80
     append
    0.79
     Appendix
    0.78
     supplement
    0.77
    append
    0.73
    appendix
    0.73
    anda
    0.70
    complement
    0.69
    Act Density 0.422%

    No Known Activations