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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "cluster" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Urbana
    -0.86
    ARGS
    -0.86
     DCE
    -0.81
    exels
    -0.81
     Manuscripts
    -0.80
     Wentworth
    -0.78
     Schae
    -0.77
     Giuliani
    -0.77
    Lähteet
    -0.76
     Huntingdon
    -0.75
    POSITIVE LOGITS
     cluster
    1.88
     clusters
    1.82
     Cluster
    1.76
    Cluster
    1.71
    cluster
    1.69
    clusters
    1.64
    CLUSTER
    1.63
     Clusters
    1.56
    Clusters
    1.53
     clustered
    1.32
    Act Density 0.061%

    No Known Activations