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

    Neuronpedia

    INDEX
    Explanations

    the phrase "how far."

    oai_token-act-pair · gpt-3.5-turbo

    references to distance or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sut
    -0.70
     Peel
    -0.68
    emis
    -0.66
    hler
    -0.66
    uala
    -0.66
    oric
    -0.66
    ificial
    -0.66
    onut
    -0.65
    kus
    -0.63
    inders
    -0.63
    POSITIVE LOGITS
    fetched
    0.81
    âĹ¼
    0.76
     Enough
    0.75
     enough
    0.72
    thing
    0.71
     awa
    0.70
     beyond
    0.68
    away
    0.67
    ï¸
    0.67
     away
    0.67
    Act Density 0.023%

    No Known Activations