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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or updates, particularly related to specific dates or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.68
    udeb
    -0.65
    dyl
    -0.65
    yang
    -0.64
    çĭ
    -0.62
    within
    -0.61
    GGGGGGGG
    -0.57
     outl
    -0.57
    iances
    -0.56
    ä¼
    -0.56
    POSITIVE LOGITS
    ths
    0.85
    mber
    0.77
     Atlantis
    0.70
     anniversary
    0.67
    IME
    0.67
     IPM
    0.66
    terday
    0.66
    tenance
    0.63
    ocket
    0.62
     partName
    0.61
    Act Density 0.055%

    No Known Activations