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

    Neuronpedia

    INDEX
    Explanations

    references to dates or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inia
    -0.20
    ÑĨеÑĢ
    -0.16
    isten
    -0.15
    riba
    -0.15
    ivos
    -0.15
    ERA
    -0.15
    698
    -0.14
    ception
    -0.14
    lector
    -0.14
    ivable
    -0.14
    POSITIVE LOGITS
    hem
    0.31
    onna
    0.29
    nard
    0.29
    oral
    0.29
    fair
    0.27
    pole
    0.26
    flower
    0.25
    ors
    0.24
    tag
    0.23
    haps
    0.23
    Act Density 0.019%

    No Known Activations