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

    Neuronpedia

    INDEX
    Explanations

    references to things that are exciting, trending, or highly in demand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ately
    -0.20
    ual
    -0.18
    ously
    -0.18
    ustin
    -0.16
     Crushers
    -0.15
    orum
    -0.15
    磨
    -0.15
    iveness
    -0.14
    (ed
    -0.14
    naires
    -0.14
    POSITIVE LOGITS
    spots
    0.23
    ting
    0.21
    -hot
    0.20
    elper
    0.18
    ening
    0.17
    -blood
    0.17
    amedi
    0.17
    rod
    0.16
    empo
    0.16
    ilities
    0.16
    Act Density 0.017%

    No Known Activations