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

    Neuronpedia

    INDEX
    Explanations

    phrases related to extending over a period or range of time or space

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duration or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licks
    -0.66
    roit
    -0.65
    Sm
    -0.63
    uctions
    -0.62
    iasis
    -0.61
    ighter
    -0.61
     behaved
    -0.61
    ILLE
    -0.59
     withhold
    -0.58
    jug
    -0.58
    POSITIVE LOGITS
    ĸļ
    0.90
     1280
    0.86
     disciplines
    0.76
     circumference
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.75
     120
    0.74
     sectors
    0.73
     spanning
    0.73
     192
    0.73
     widest
    0.73
    Act Density 0.120%

    No Known Activations