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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "real" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ew
    -0.18
    eday
    -0.17
    edn
    -0.17
    ed
    -0.16
    ese
    -0.16
    esh
    -0.16
    eldorf
    -0.16
    enko
    -0.16
    osal
    -0.15
    oretical
    -0.15
    POSITIVE LOGITS
    istically
    0.20
    located
    0.20
    igned
    0.19
    ignment
    0.18
    locate
    0.17
    -life
    0.17
    ising
    0.17
    tors
    0.17
    -world
    0.17
    isation
    0.17
    Act Density 0.039%

    No Known Activations