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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and the importance of community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    variants
    -0.15
    andel
    -0.14
    .GetText
    -0.14
    ak
    -0.14
    ért
    -0.13
     Continent
    -0.13
     Succ
    -0.13
    ack
    -0.13
    .='
    -0.13
    avian
    -0.13
    POSITIVE LOGITS
     beyond
    0.51
     Beyond
    0.41
    Beyond
    0.38
    eyond
    0.36
     besides
    0.35
     além
    0.34
     oltre
    0.28
     кÑĢоме
    0.24
     Besides
    0.23
     deeper
    0.22
    Act Density 0.208%

    No Known Activations