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

    Neuronpedia

    INDEX
    Explanations

    references to job titles and organizational roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Brains
    -0.16
    .Geometry
    -0.16
    .createFrom
    -0.16
     JAXBElement
    -0.15
    atural
    -0.15
    /graphql
    -0.15
     giỼi
    -0.15
    еко
    -0.14
    lep
    -0.14
    .rawValue
    -0.14
    POSITIVE LOGITS
    0.17
    ilter
    0.16
    egal
    0.14
    regist
    0.14
     tiener
    0.14
    anging
    0.14
     content
    0.14
    icky
    0.14
     mod
    0.13
     expo
    0.13
    Act Density 0.041%

    No Known Activations