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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and metrics related to research results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akov
    -0.14
    SCREEN
    -0.14
    DBus
    -0.14
    umba
    -0.14
     here
    -0.14
     Silver
    -0.14
    umer
    -0.14
    ož
    -0.14
     right
    -0.14
     Brend
    -0.14
    POSITIVE LOGITS
    heits
    0.16
    ëĮĢ
    0.15
    yan
    0.14
    asion
    0.14
    &lt
    0.13
    ãĤ´ãĥª
    0.13
    innitus
    0.13
    opsis
    0.13
    ло
    0.13
    аÑĤ
    0.13
    Act Density 0.011%

    No Known Activations