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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "real" or "real-life."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.21
    esh
    -0.21
    ed
    -0.21
    ese
    -0.20
    esis
    -0.17
    edn
    -0.17
    edImage
    -0.16
    dale
    -0.16
    es
    -0.16
    sing
    -0.15
    POSITIVE LOGITS
    istically
    0.28
    igned
    0.25
    istic
    0.21
    fully
    0.21
    ignment
    0.21
    located
    0.18
    -life
    0.18
    izations
    0.18
    ikel
    0.18
    undo
    0.17
    Act Density 0.040%

    No Known Activations