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

    Neuronpedia

    INDEX
    Explanations

    keywords related to test data or test-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mlink
    -0.16
    gie
    -0.16
    upp
    -0.15
    иÑģÑĮ
    -0.15
    udad
    -0.14
     Challenger
    -0.14
    soever
    -0.14
    ming
    -0.13
    upil
    -0.13
     unp
    -0.13
    POSITIVE LOGITS
    niž
    0.16
    borg
    0.15
     اÙĦعÙħ
    0.15
    оÑĢод
    0.15
    idot
    0.15
    DDS
    0.15
    ikel
    0.14
     chân
    0.14
     nowrap
    0.14
    .jupiter
    0.14
    Act Density 0.039%

    No Known Activations