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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clusters of objects or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "cluster" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hran
    -0.81
    estamp
    -0.71
    inburgh
    -0.68
    Ö¼
    -0.66
    verson
    -0.65
    ebus
    -0.65
    toc
    -0.65
    issance
    -0.65
     Dame
    -0.65
    enegger
    -0.64
    POSITIVE LOGITS
    fuck
    1.10
     cluster
    0.97
     clusters
    0.95
     bom
    0.93
    mates
    0.86
    usters
    0.81
     grouping
    0.77
     clustered
    0.74
     weaving
    0.72
     filler
    0.70
    Act Density 0.011%

    No Known Activations