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

    Neuronpedia

    INDEX
    Explanations

    date references, specifically formatted as "Mar" followed by a numeral

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.18
    rus
    -0.17
    ios
    -0.17
    RX
    -0.17
    ense
    -0.17
    yu
    -0.16
    룬
    -0.16
    sing
    -0.16
    ema
    -0.16
    iou
    -0.15
    POSITIVE LOGITS
    oon
    0.23
    quis
    0.22
    oons
    0.22
    quee
    0.20
    shall
    0.20
    bles
    0.20
    antz
    0.19
    coni
    0.18
    ques
    0.18
    riages
    0.18
    Act Density 0.021%

    No Known Activations