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

    Neuronpedia

    INDEX
    Explanations

    references to secretive organizations or concepts, particularly those denoted as "secret."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.17
    erken
    -0.17
    uppy
    -0.17
    uteur
    -0.16
    umi
    -0.15
    лаб
    -0.15
    olicit
    -0.14
    akk
    -0.14
    ermen
    -0.14
    UnderTest
    -0.14
    POSITIVE LOGITS
    ariat
    0.25
    iveness
    0.21
    ácil
    0.16
    aries
    0.16
    à¹Ģà¸ģà¸Ńร
    0.15
    /conf
    0.15
    ivec
    0.15
    arial
    0.15
    ensely
    0.15
    ively
    0.15
    Act Density 0.018%

    No Known Activations