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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erp
    -0.15
    -Oct
    -0.14
    -Jan
    -0.14
    feeds
    -0.14
    -Sep
    -0.14
    wij
    -0.14
    irate
    -0.14
    aney
    -0.14
    iž
    -0.13
    alone
    -0.13
    POSITIVE LOGITS
     instant
    0.20
     Instant
    0.18
    .instant
    0.17
    illet
    0.17
     Pra
    0.16
    ÑĢовод
    0.16
    illos
    0.16
     ÑĩиÑģла
    0.16
     century
    0.16
    -century
    0.15
    Act Density 0.030%

    No Known Activations