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

    Neuronpedia

    INDEX
    Explanations

    phrases summarizing or encapsulating information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to summarizing or condensing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iae
    -0.70
    airs
    -0.66
    iaries
    -0.65
    back
    -0.62
     proxies
    -0.61
    eland
    -0.61
    iaz
    -0.61
    roid
    -0.60
    iannopoulos
    -0.60
     harb
    -0.58
    POSITIVE LOGITS
     succinct
    1.01
     summed
    0.82
     concise
    0.81
    Ĥª
    0.81
    tten
    0.76
    ãĥ¼ãĥ³
    0.72
     summarizes
    0.72
     bluntly
    0.72
    ¢
    0.72
     neatly
    0.72
    Act Density 0.079%

    No Known Activations