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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "normalcy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eling
    -0.18
    ILE
    -0.15
    roupe
    -0.14
    inous
    -0.14
    eli
    -0.14
    eb
    -0.14
    NullException
    -0.14
    anical
    -0.14
    ampler
    -0.14
    essel
    -0.14
    POSITIVE LOGITS
    mente
    0.21
    cy
    0.21
    ity
    0.20
    -normal
    0.19
    ities
    0.19
    cott
    0.19
    izr
    0.17
    afen
    0.17
    -sized
    0.16
    ously
    0.15
    Act Density 0.033%

    No Known Activations