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

    Neuronpedia

    INDEX
    Explanations

    comparisons of various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comparison" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.66
    iscovery
    -0.65
     havoc
    -0.64
    eland
    -0.64
    ãĥİ
    -0.64
    ieri
    -0.64
    tails
    -0.63
    ighth
    -0.63
    haw
    -0.62
    jong
    -0.62
    POSITIVE LOGITS
    ogue
    0.87
     apples
    0.82
     comparing
    0.82
     comparisons
    0.80
    xual
    0.77
     between
    0.76
     favorably
    0.75
     comparison
    0.75
    isons
    0.72
     compare
    0.70
    Act Density 0.034%

    No Known Activations