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

    Neuronpedia

    INDEX
    Explanations

    terms related to clusters, particularly mentioning the word "cluster" several times at varying activations

    oai_token-act-pair · gpt-3.5-turbo

    references to "clusters," indicating groupings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hran
    -0.80
    Ö¼
    -0.76
    ODUCT
    -0.68
    PLIED
    -0.68
    orters
    -0.68
    inen
    -0.67
    toc
    -0.67
    inburgh
    -0.67
    tek
    -0.65
    ebus
    -0.65
    POSITIVE LOGITS
    fuck
    1.15
     bom
    0.96
    usters
    0.91
     clusters
    0.89
     cluster
    0.84
    mates
    0.77
     geographically
    0.72
     headaches
    0.71
     clustered
    0.69
     grouping
    0.68
    Act Density 0.031%

    No Known Activations