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

    Neuronpedia

    INDEX
    Explanations

    Java code elements related to boolean access control and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.17
    кап
    -0.16
    vů
    -0.15
    tainment
    -0.15
    .setter
    -0.15
    cies
    -0.15
    innie
    -0.14
    ekil
    -0.14
     ÙħÛĮÙĦادÛĮ
    -0.14
    enko
    -0.14
    POSITIVE LOGITS
    иÑĢ
    0.15
     |=
    0.15
    orrow
    0.15
    ä½į
    0.15
    mask
    0.15
     mask
    0.14
    tet
    0.14
     tet
    0.14
    gram
    0.14
     masks
    0.14
    Act Density 0.042%

    No Known Activations